© 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. 8822
    Prev
    Next
    INDEX
    Explanations

    references to graphical elements or styles in illustrations or diagrams

    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
    ContentAsync
    -0.46
    joey
    -0.41
     escuchado
    -0.40
     salvare
    -0.39
     informée
    -0.38
     tenham
    -0.38
    ęć
    -0.38
     oreilles
    -0.38
     venge
    -0.38
     camiones
    -0.38
    POSITIVE LOGITS
     ſch
    0.54
     ſte
    0.54
     مشين
    0.49
    +:+
    0.46
     ſche
    0.44
    Personensuche
    0.43
     viſ
    0.43
     ſon
    0.43
     linkovi
    0.42
     Houſe
    0.42
    Activations Density 0.421%

    No Known Activations