© 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
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 8869
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to function declarations and calls

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    chieht
    -0.47
     myö
    -0.46
     entendido
    -0.45
     oeil
    -0.44
     entiende
    -0.43
    errHandler
    -0.42
     cárcel
    -0.42
     latter
    -0.42
     recientemente
    -0.42
     quiera
    -0.42
    POSITIVE LOGITS
    __":
    0.43
    __::
    0.42
     sond
    0.41
     resourceCulture
    0.40
    entiel
    0.40
    goto
    0.40
     numeral
    0.39
    elemField
    0.38
    kháu
    0.38
     localObject
    0.38
    Activations Density 0.229%

    No Known Activations