Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8083
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and parameters, particularly those associated with code syntax and data structures

    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
    MessageOf
    -0.96
    MessageTagHelper
    -0.73
    setVerticalGroup
    -0.73
     pinulongan
    -0.70
     kohdetta
    -0.67
    IntoConstraints
    -0.66
    ViewFeatures
    -0.60
    webElementXpaths
    -0.59
     invokingState
    -0.59
    enderror
    -0.59
    POSITIVE LOGITS
    setScene
    0.34
     transférez
    0.32
     AssemblyTitle
    0.32
    withIdentifier
    0.31
     [][]
    0.31
     fopen
    0.29
    &__
    0.29
    internalType
    0.29
    мое
    0.29
     пластик
    0.29
    Activations Density 0.029%

    No Known Activations