© 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. 93016
    Prev
    Next
    INDEX
    Explanations

    references to art, documentation, and the organization of information

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

    work of art

    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
    лтемелер
    -0.42
    ⓧ
    -0.40
    spesies
    -0.38
    hoch
    -0.32
    Семья
    -0.32
     امید
    -0.32
     mystère
    -0.31
     Fassung
    -0.31
    談社
    -0.30
     réduit
    -0.30
    POSITIVE LOGITS
    IntoConstraints
    0.61
     AssemblyCulture
    0.59
    fillType
    0.54
    InitVars
    0.53
    writeFieldEnd
    0.51
    InstrumentedTest
    0.50
    lusconi
    0.49
     tartalomajánló
    0.48
    graffiti
    0.48
    Santis
    0.47
    Activations Density 0.629%

    No Known Activations