© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 72792
    Prev
    Next
    INDEX
    Explanations

    statements related to coding imports and constants in programming

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    Negative Logits
    Identity
    -0.25
    auth
    -0.24
    在
    -0.24
    2
    -0.24
    ;
    -0.24
    a
    -0.24
    app
    -0.24
    0
    -0.24
    1
    -0.23
    style
    -0.23
    POSITIVE LOGITS
    adaptiveStyles
    1.04
     autorytatywna
    0.96
    تقاوى
    0.94
    rungsseite
    0.92
    tagHelperRunner
    0.90
     للمعارف
    0.89
     kasarigan
    0.87
     nakalista
    0.84
     snippetHide
    0.84
    ftagPool
    0.84
    Activations Density 0.001%

    No Known Activations