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. 73569
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical constructs or specific variables in formal contexts

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

    Text components that function as technical terminology, reference markers, or specialized identifiers within structured academic, scientific, or technical documents.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     ProtoMessage
    -0.35
     Malle
    -0.35
     proof
    -0.32
    ModuleName
    -0.32
     grew
    -0.31
    jooq
    -0.31
    σσ
    -0.31
    ječ
    -0.31
    FORMANCE
    -0.29
     σ
    -0.29
    POSITIVE LOGITS
    
    0.64
    writeFieldEnd
    0.63
    fromnode
    0.62
     AssemblyCulture
    0.60
    LabelTagHelper
    0.58
     noDo
    0.58
    jsxFileName
    0.58
    bnf
    0.54
    دانشنامهٔ
    0.54
    ViewFeatures
    0.53
    Activations Density 0.032%

    No Known Activations