© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 85925
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax in programming languages

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

    user code sections

    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
    HostException
    -0.40
    inhalt
    -0.34
     chaos
    -0.33
    äsenti
    -0.32
     biomarkers
    -0.31
    ρεύ
    -0.30
    setViewName
    -0.30
    Chaos
    -0.30
     Allianz
    -0.29
    openConnection
    -0.29
    POSITIVE LOGITS
    oa̍t
    0.60
    LookAnd
    0.57
     surla
    0.55
    contentLoaded
    0.55
    UrlResolution
    0.51
     său
    0.48
     idéia
    0.48
    DebuggerStep
    0.47
    msgTypes
    0.47
    forChild
    0.47
    Activations Density 0.011%

    No Known Activations