Gemma

Definition

Plain language

Google's family of open-weight smaller language models.

Also called: Gemma-2, Gemma-3, Gemma three, Gemma-3-12B

Why it matters: Open-weight small models like Gemma are what makes most interpretability and academic AI research possible.

For example, researchers studying how transformers store factual knowledge often pick a Gemma 2B model because the weights are open and the size is manageable on a single GPU.

Heard on the show

“Llama, Gemma, scored the same rigged answers.”

Mentioned in 15 episodes

1. 207
   An AI Graded Its Own Math Test 94 Percent — It Actually Scored 20
2. 179
   How DeepSeek Made One User Faster Without Slowing Down the Crowd
3. 173
   The Free Step-Level Grader Hiding in Every RL Training Run
4. 143
   When a Model Notices You Forged Its Own Words, And Why That Breaks Safety Tests
5. 140
   When a Reasoning Model Says "Let Me Double-Check" After It's Already Decided
6. 118
   Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm
7. 107
   How a Market of Crippled AI Agents Outscored One Unrestricted Model
8. 074
   How a Fifteen-Hundred-Dollar Training Run Matched Llama and Gemma on Reasoning
9. 055
   Why LLM Judges Flip Their Verdicts When You Change the Question Format
10. 038
    How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
11. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
12. 032
    A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
13. 013
    Why Search Keeps Rediscovering the Same Workflow, and What That Means
14. 008
    Why Long-Horizon AI Agents Get Stuck, and a Milestone-Based Fix That Helps
15. 004
    The Sycophancy Circuit That Survives Alignment Training

Related terms