Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 86989
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structural elements in a document

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

    path

    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
     ब्रेकडाउन
    -0.76
     Biôgrafia
    -0.67
    UserScript
    -0.66
     שוליים
    -0.63
    AccessorTable
    -0.62
    !*\
    -0.61
    endpush
    -0.61
    
    -0.60
    ndice
    -0.60
     CURIAM
    -0.60
    POSITIVE LOGITS
    ViewFeatures
    0.28
    プライズ
    0.23
    ">//
    0.22
    ◄
    0.21
     physiques
    0.20
    最大的
    0.20
    Produzione
    0.20
    habitude
    0.20
    Einzelnachweise
    0.20
    优雅
    0.19
    Activations Density 0.001%

    No Known Activations