© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 3395
    Prev
    Next
    INDEX
    Explanations

    references to watching or viewing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abp
    -0.82
    ])),
    -0.81
    (;;)
    -0.76
    ']),
    -0.74
    }}],
    -0.71
    })),
    -0.70
     Damian
    -0.69
    />";
    -0.69
     للمعارف
    -0.67
     Clough
    -0.67
    POSITIVE LOGITS
     watch
    1.94
     Watch
    1.84
     WATCH
    1.84
     watches
    1.73
    watch
    1.70
    Watch
    1.67
     Watches
    1.67
    WATCH
    1.62
    watches
    1.61
     Watched
    1.61
    Activations Density 0.037%

    No Known Activations