© 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. 10374
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to equations and transformations

    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
    帖最后由
    -0.93
    TagMode
    -0.88
    windowFixed
    -0.84
    transQ
    -0.83
    RenderAtEndOf
    -0.73
    SharedCtor
    -0.71
     kaarangay
    -0.71
    Personensuche
    -0.70
    GEBURTSDATUM
    -0.69
    RegressionTest
    -0.68
    POSITIVE LOGITS
     EdgeInsets
    0.39
    Lat
    0.35
     Vito
    0.34
    Cy
    0.33
     Run
    0.33
     prioritized
    0.32
    Run
    0.32
    run
    0.32
     hammered
    0.31
     run
    0.31
    Activations Density 0.767%

    No Known Activations