© 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. 21-GEMMASCOPE-RES-16K
    11. 10495
    Prev
    Next
    INDEX
    Explanations

    code structures and logic in programming languages

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Италијани
    -1.15
     للمعارف
    -1.02
     ujednoznacz
    -0.88
     Italijanski
    -0.86
    AndEndTag
    -0.82
     propOrder
    -0.81
    WithIOException
    -0.77
    IntoConstraints
    -0.77
    цездатний
    -0.76
     Chwiliwch
    -0.75
    POSITIVE LOGITS
     ,
    0.39
    Code
    0.36
    텐츠
    0.31
     ignore
    0.31
    App
    0.31
     fra
    0.30
     cœurs
    0.30
     sti
    0.29
     Llo
    0.28
    QList
    0.28
    Activations Density 0.250%

    No Known Activations