← Back to Explorer
Evaluation 505 of 723
Evaluation
Personal Data
automated filtering of personal information from training data plus measurement of how many memorized outputs contain sensitive or personal data, classified with Google Cloud Sensitive Data Protection (three severity levels; highest classified 'sensitive', the other two 'personal')
Memorization & privacy
Google DeepMind — Gemma
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.
Gemma 1
Feb 2024
Google DeepMind — Gemma
partial detail
21 method fields published
See how this test was run
Gemma model card | Google AI for Developers · Feb 2024
Gemma model card | Google AI for Developers · Feb 2024
Gemma model card | Google AI for Developers · Feb 2024
Gemma model card | Google AI for Developers · Feb 2024
Gemma model card | Google AI for Developers · Feb 2024
Gemma model card | Google AI for Developers · Feb 2024
Gemma 2
Jun 2024
Google DeepMind — Gemma
partial detail
21 method fields published
See how this test was run
Gemma 2 model card | Google AI for Developers · Jun 2024
Gemma 2 model card | Google AI for Developers · Jun 2024
Gemma 2 model card | Google AI for Developers · Jun 2024
Gemma 2 model card | Google AI for Developers · Jun 2024
Gemma 2 model card | Google AI for Developers · Jun 2024
Gemma 2 model card | Google AI for Developers · Jun 2024
Gemma 2 model card | Google AI for Developers · Jun 2024