CodeGemma
Google DeepMind — Gemma
partial detail 14 method fields published
Evaluation
Ethics and safety evaluation (content safety, representational harms)
human evaluation on prompts covering content safety and representational harms (see the Gemma model card for more details on evaluation approach)
How it was run
Open a release to see the setup, scoring, and other details that the lab published. Only fields the lab actually disclosed are shown.