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. 102986
    Prev
    Next
    INDEX
    Explanations

    opening parentheses in code

    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
     CanadaChoose
    -0.43
     Biôgrafia
    -0.39
    UseVisualStyle
    -0.39
    encodeWith
    -0.38
     hatch
    -0.38
     pitching
    -0.38
    astify
    -0.37
     inqu
    -0.36
    reactstrap
    -0.36
    枢
    -0.36
    POSITIVE LOGITS
    IUrlHelper
    0.68
     AssemblyCompany
    0.64
     EconPapers
    0.60
    VIAF
    0.49
    Diweddarwch
    0.49
    StructEnd
    0.49
     vantaggi
    0.48
    ViewFeatures
    0.48
    oa̍t
    0.48
    MigrationBuilder
    0.47
    Activations Density 0.000%

    No Known Activations