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

    Neuronpedia

    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. 1339
    Prev
    Next
    INDEX
    Explanations

    components and references related to software and programming frameworks

    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
     AssemblyCulture
    -0.56
    webElementXpaths
    -0.56
     esternos
    -0.53
    Hentet
    -0.46
    complexContent
    -0.45
    RenderAtEndOf
    -0.44
     ویکی‌پدی
    -0.44
    QMetaType
    -0.42
    Viungo
    -0.42
    zczegól
    -0.41
    POSITIVE LOGITS
    ApplicationTests
    0.80
     project
    0.58
     MaterialApp
    0.56
     app
    0.54
     ApiClient
    0.53
     application
    0.53
    app
    0.52
     viewer
    0.52
    App
    0.50
     приложение
    0.50
    Activations Density 0.761%

    No Known Activations