© 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. 36-GEMMASCOPE-RES-16K
    11. 5012
    Prev
    Next
    INDEX
    Explanations

    code-related structures and syntax elements, primarily focusing on method definitions and properties

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     décid
    -0.37
     forfait
    -0.35
     remet
    -0.34
     Bidang
    -0.34
     contesta
    -0.33
    oiseau
    -0.33
    Tho
    -0.33
    Vaata
    -0.32
    CompleteListener
    -0.31
    FAR
    -0.30
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
    NameInMap
    0.59
    BeginContext
    0.53
    Derbyniad
    0.50
    "));
    0.50
     Obrador
    0.49
     
    0.49
    Rcpp
    0.48
     estekak
    0.48
    .");
    0.47
    Activations Density 0.613%

    No Known Activations