© 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. 21375
    Prev
    Next
    INDEX
    Explanations

    specific alphanumeric characters or patterns that could indicate variables or identifiers in a code or technical context

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

    figures and legal citations

    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
     AssemblyProduct
    -0.44
    DIPSETTING
    -0.43
    adaptiveStyles
    -0.43
     farther
    -0.43
    beho
    -0.40
    strö
    -0.39
     onStop
    -0.39
     لينك
    -0.39
    OOTDTY
    -0.39
    lyst
    -0.38
    POSITIVE LOGITS
     nahilalakip
    0.93
     autorytatywna
    0.69
    SharedCtor
    0.60
     Roskov
    0.56
    OGND
    0.54
    PerformLayout
    0.52
    KommentareTeilen
    0.52
    Географиясе
    0.49
     nakalista
    0.48
    :✨
    0.47
    Activations Density 0.001%

    No Known Activations