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. 73446
    Prev
    Next
    INDEX
    Explanations

    code constructs related to file handling operations

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

    JavaScript/Node.js function closures that handle asynchronous operations, particularly callback patterns at the end of function blocks and function returns.

    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
     defaultstate
    -0.84
     EconPapers
    -0.77
     ujednoznacz
    -0.74
    AnchorStyles
    -0.73
    principalTable
    -0.73
    RTEE
    -0.72
     queſta
    -0.69
    ReusableCell
    -0.65
    ésultats
    -0.63
    ſchaft
    -0.63
    POSITIVE LOGITS
    回
    0.34
     leading
    0.31
     [
    0.31
    awaiter
    0.31
    StartCoroutine
    0.31
    倒
    0.30
     immediately
    0.30
     native
    0.30
     çek
    0.30
     Lovel
    0.29
    Activations Density 0.221%

    No Known Activations