Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53482
    Prev
    Next
    INDEX
    Explanations

    elements related to function calls and code structure in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.91
    transQ
    -0.77
     defaultstate
    -0.77
    GEBURTSDATUM
    -0.75
    ConstraintMaker
    -0.73
     للمعارف
    -0.73
    RenderAtEndOf
    -0.72
     MainAxisSize
    -0.70
    AutoScaleMode
    -0.69
    __":
    
    -0.67
    POSITIVE LOGITS
     transmite
    0.41
    Hence
    0.35
     hence
    0.34
     Hence
    0.34
     transmitir
    0.33
    <strong>
    0.33
     ardından
    0.32
    because
    0.32
    
    0.31
      
    0.31
    Activations Density 0.014%

    No Known Activations