© 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. 31850
    Prev
    Next
    INDEX
    Explanations

    references to measurements and specifications related to speed, height, and rate

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

    quantifiable physical dimensions or rates

    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
    transQ
    -0.85
    fjspx
    -0.73
    EndContext
    -0.69
     ProtoMessage
    -0.66
    utnik
    -0.65
     للاسماء
    -0.61
    BeginContext
    -0.60
    ReusableCell
    -0.59
     disambiguazione
    -0.57
    Notae
    -0.57
    POSITIVE LOGITS
    TintMode
    0.34
    Opened
    0.33
    うちに
    0.31
     Keil
    0.30
     recorrido
    0.29
     Reeve
    0.29
    utura
    0.29
    miro
    0.28
    Utc
    0.28
     Kelle
    0.28
    Activations Density 0.063%

    No Known Activations