© 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. 87277
    Prev
    Next
    INDEX
    Explanations

    references to humorous and light-hearted experiences or interactions

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

    money and quantities

    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
    glise
    -0.35
     StatefulWidget
    -0.33
     reager
    -0.31
    sprozess
    -0.30
     teams
    -0.30
    Erreferentziak
    -0.28
     realizacji
    -0.28
     wyłącznie
    -0.28
     Leiter
    -0.28
     cordones
    -0.28
    POSITIVE LOGITS
     فريبيس
    0.78
     AssemblyCulture
    0.71
    いかがでしょうか
    0.67
     refreshing
    0.64
    posedge
    0.63
     somethin
    0.63
    MessageOf
    0.63
    bootstrapcdn
    0.63
    Билгалдахарш
    0.62
    发表于
    0.61
    Activations Density 0.044%

    No Known Activations