© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8032
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Webber
    -0.76
    bootstrapcdn
    -0.73
    MINOR
    -0.71
    ly
    -0.69
    {{{
    -0.69
    aarrggbb
    -0.68
    t
    -0.68
     McCormack
    -0.66
    board
    -0.66
     berke
    -0.66
    POSITIVE LOGITS
    <h5>
    1.83
    <h6>
    1.30
    </h5>
    1.19
     שוליים
    0.96
     occaf
    0.93
     PLS
    0.93
     
    0.92
     Tolstoy
    0.90
    évaluateur
    0.87
     CommonModule
    0.87
    Activations Density 0.320%

    No Known Activations