Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior

T1Covered by 1 source · first reported by Google — The Keyword / AI / Research / DeepMind / Developers at 16 Dec 2025, 10:14 UTC

Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.

releases

Sources

• T1Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behaviorGoogle — The Keyword / AI / Research / DeepMind / Developers16 Dec 2025, 10:14