© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6739
    Prev
    Next
    INDEX
    Explanations

    instances of injury and surgical procedures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Derbyniad
    -0.59
     informée
    -0.54
    EndProject
    -0.53
     AssemblyCulture
    -0.48
    apunov
    -0.47
    RTLI
    -0.46
     disambiguazione
    -0.45
    RTEE
    -0.45
    openzeppelin
    -0.43
    setVerticalGroup
    -0.43
    POSITIVE LOGITS
     cut
    3.78
     Cut
    3.38
    Cut
    3.30
    cut
    3.28
     cuts
    3.23
     CUT
    3.11
     cutting
    3.11
    CUT
    2.92
     Cutting
    2.88
     Cuts
    2.86
    Activations Density 1.238%

    No Known Activations