© 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. 27648
    Prev
    Next
    INDEX
    Explanations

    structured data elements, specifically indicating elements and attributes typical in programming or data schema definitions

    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
    OGND
    -0.97
     Administrativna
    -0.92
    PerformLayout
    -0.91
     MainAxisSize
    -0.85
     ویکی‌پدی
    -0.85
    featureID
    -0.84
    دانشنامهٔ
    -0.84
     незавершена
    -0.83
     queſta
    -0.82
    ロウィン
    -0.82
    POSITIVE LOGITS
     is
    0.37
    ↵
    0.37
    Pen
    0.36
     {
    0.36
     de
    0.33
     I
    0.32
     (
    0.32
    {
    0.32
     i
    0.31
    Inter
    0.30
    Activations Density 0.028%

    No Known Activations