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. 122968
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements

    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
    jsxFileName
    -0.41
     plan
    -0.40
    LookAnd
    -0.39
    PreExecute
    -0.36
     förstå
    -0.36
     돌
    -0.35
    arti
    -0.34
     interaction
    -0.33
     similar
    -0.33
    ugu
    -0.33
    POSITIVE LOGITS
     betweenstory
    0.80
    exitRule
    0.57
     estekak
    0.57
    Geplaatst
    0.56
    StoryboardSegue
    0.55
    AsUp
    0.54
     propOrder
    0.52
    BagConstraints
    0.51
    asteroide
    0.50
     Vacant
    0.50
    Activations Density 0.031%

    No Known Activations