© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 107517
    Prev
    Next
    INDEX
    Explanations

    specific HTML or website-related content

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

    non-english words

    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
    elemField
    -0.55
     GenerationType
    -0.50
    tribune
    -0.45
    inSlope
    -0.43
     kona
    -0.43
     reliefs
    -0.42
     sumpay
    -0.41
     versa
    -0.41
     estimés
    -0.41
    MMV
    -0.40
    POSITIVE LOGITS
    клопе
    0.45
     ब्रेकडाउन
    0.39
    odacty
    0.39
    Tembelea
    0.37
    요
    0.36
    actionMode
    0.35
    ỡng
    0.35
     CanadaChoose
    0.35
     Photocase
    0.35
    osted
    0.35
    Activations Density 0.068%

    No Known Activations