© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 69151
    Prev
    Next
    INDEX
    Explanations

    API-related terms and data structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    JavaScript, Go, or Java code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    -0.35
    3
    -0.34
    Read
    -0.32
     his
    -0.32
    //
    -0.32
    Json
    -0.32
    @
    -0.31
     hear
    -0.31
    -
    -0.31
    LogUtil
    -0.31
    POSITIVE LOGITS
    BagConstraints
    2.02
    tableFuture
    1.46
    ClientRect
    1.43
    TargetException
    1.38
    BagLayout
    1.36
    orianCalendar
    1.34
    parsedMessage
    1.31
    CPtr
    1.29
    LayoutPanel
    1.22
    ObjectContext
    1.13
    Activations Density 0.003%

    No Known Activations