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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105802
    Prev
    Next
    INDEX
    Explanations

    programming terms related to software development and API implementations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    LookAnd
    -0.56
    getWriter
    -0.46
     productor
    -0.34
     Bourgoin
    -0.30
    ceptar
    -0.29
     racine
    -0.29
     Gór
    -0.28
     ffilm
    -0.27
    ValueOf
    -0.27
    IsContent
    -0.26
    POSITIVE LOGITS
    DrawerToggle
    1.68
    serde
    1.67
    flink
    1.28
    scalatest
    1.23
     serde
    1.20
    HandlerContext
    1.03
     Codable
    0.99
    tableFuture
    0.90
    FXMLLoader
    0.86
    openzeppelin
    0.84
    Activations Density 0.001%

    No Known Activations