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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35393
    Prev
    Next
    INDEX
    Explanations

    punctuation and syntax-related constructs in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     AssemblyCompany
    -0.64
     intptr
    -0.59
     nonUne
    -0.56
    writeField
    -0.56
     AssemblyTitle
    -0.56
    inSlope
    -0.54
    󠁢
    -0.53
    :✨
    -0.52
    TypedDataSet
    -0.51
    oa̍t
    -0.51
    POSITIVE LOGITS
    arynx
    0.36
    OnError
    0.34
    antası
    0.34
     élus
    0.34
    odiment
    0.34
     visiteurs
    0.33
     bénévoles
    0.33
    ResponseEntity
    0.32
    RTEX
    0.31
     traffico
    0.31
    Activations Density 0.001%

    No Known Activations