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. 73627
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to setting up user interface elements and callbacks

    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
    ValueStyle
    -0.67
     виправивши
    -0.59
    WriteAttribute
    -0.56
    bewerken
    -0.54
    AutoField
    -0.53
    principalTable
    -0.52
    usermodel
    -0.52
    drawSprites
    -0.52
    GEBURTS
    -0.52
    Viitteet
    -0.50
    POSITIVE LOGITS
    ViewFeatures
    0.33
     fundo
    0.31
     flèche
    0.29
    ideos
    0.29
     Conroy
    0.28
    ekt
    0.27
     distanciation
    0.27
    kusen
    0.27
     enví
    0.27
    accro
    0.26
    Activations Density 0.061%

    No Known Activations