© 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. 90117
    Prev
    Next
    INDEX
    Explanations

    elements of structured data and references in code annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    AutoScaleMode
    -0.63
    djangoproject
    -0.59
    parsedMessage
    -0.57
     gyhoeddwyd
    -0.54
    Décès
    -0.54
     jsPsych
    -0.53
     BoxDecoration
    -0.52
    Xna
    -0.51
     AssemblyCompany
    -0.50
     initComponents
    -0.49
    POSITIVE LOGITS
     مشين
    0.49
    HasIndex
    0.41
     suje
    0.41
     îl
    0.38
     pelig
    0.38
     gostar
    0.38
     Ordnung
    0.38
    antenimiento
    0.37
     Vázquez
    0.37
    Poor
    0.36
    Activations Density 0.006%

    No Known Activations