Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 131039
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax in programming languages

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

    Code syntax elements that serve as block terminators, expression connectors or operators in programming languages, such as closing braces, arrow function notation, or underscore characters in identifiers.

    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
    SharedDtor
    -0.72
    saraba
    -0.54
    脚注の使い方
    -0.51
     Chwiliwch
    -0.51
     دیکھیے
    -0.50
    ItemBackground
    -0.50
    principalColumn
    -0.49
    ագրություններ
    -0.46
    Cyfarwyddwr
    -0.46
    rmızı
    -0.44
    POSITIVE LOGITS
     createSlice
    0.77
    orylation
    0.38
     StatelessWidget
    0.38
     मिल
    0.36
     recepto
    0.35
     دور
    0.34
     Study
    0.34
    Cubit
    0.33
    AndroidJUnit
    0.33
     Designer
    0.33
    Activations Density 0.003%

    No Known Activations