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. 131046
    Prev
    Next
    INDEX
    Explanations

    Terminology and concepts related to technical systems and devices

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

    Small punctuation marks, functional words, and technical terminology that serve as structural connectors in formal text such as code, scientific writing, or legal 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
    )}}{
    -0.37
     therefore
    -0.35
     front
    -0.35
    ok
    -0.34
     refor
    -0.34
    OK
    -0.32
     cop
    -0.32
    整
    -0.32
    Découvrez
    -0.32
     dig
    -0.32
    POSITIVE LOGITS
    DockStyle
    0.76
    invokeLater
    0.68
     <<<<<<<<<<<<<<
    0.68
    BagConstraints
    0.65
    tanleria
    0.63
    发表于
    0.63
    Personensuche
    0.63
     Biôgrafia
    0.62
    verwijspagina
    0.62
    AddHtmlAttribute
    0.61
    Activations Density 0.147%

    No Known Activations