© 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. 122221
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "import" within programming contexts

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

    code imports starting with io

    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
     Garantía
    -0.56
     OMITBAD
    -0.53
     Comprometido
    -0.53
    transQ
    -0.52
    SEGUIR
    -0.51
     Capacidad
    -0.50
    Atentamente
    -0.49
    étoit
    -0.48
     mijne
    -0.48
    -------------</
    -0.48
    POSITIVE LOGITS
    io
    0.64
     piped
    0.59
    idio
    0.57
     IO
    0.54
     stream
    0.54
     io
    0.52
     streaming
    0.52
    reactivex
    0.51
     streams
    0.50
     diode
    0.50
    Activations Density 0.001%

    No Known Activations