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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 73455
    Prev
    Next
    INDEX
    Explanations

    phrases indicating responsibility or accountability in contexts related to health and safety

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

    specifies definite nouns

    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
     ulasan
    -0.36
     Autorizaciones
    -0.33
     Vorder
    -0.32
    fæ
    -0.32
    глед
    -0.31
     Majesté
    -0.30
    principalTable
    -0.30
    IMENTAL
    -0.30
     continúas
    -0.29
     onView
    -0.29
    POSITIVE LOGITS
    transQ
    0.85
    expandindo
    0.77
    WithIOException
    0.68
     Италијани
    0.64
     мәкал
    0.64
     ब्रेकडाउन
    0.62
     дописавши
    0.60
    $_['
    0.59
    OGND
    0.59
    Хьажоргаш
    0.59
    Activations Density 0.037%

    No Known Activations