© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 38296
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.46
    ppuden
    -0.45
    signor
    -0.44
    evaluator
    -0.44
    encodeWith
    -0.41
    evaluate
    -0.40
    chalet
    -0.40
    rawDesc
    -0.40
    server
    -0.39
    Vidite
    -0.39
    POSITIVE LOGITS
    Bronnen
    2.09
     odkazy
    0.57
    Referenties
    0.57
     estekak
    0.54
     Paglinawan
    0.48
    期刊论文
    0.46
    rungsseite
    0.46
     jsPsych
    0.42
    #
    0.41
     flesta
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.