© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41260
    Prev
    Next
    INDEX
    Explanations

    questions and directives typically seen in mathematical or logical problem-solving contexts

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

    let

    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
     AssemblyCulture
    -0.80
    цездатний
    -0.67
    ValueStyle
    -0.62
    oredCriteria
    -0.56
     mijne
    -0.54
    rungsseite
    -0.54
    Aholisi
    -0.52
    LookAnd
    -0.52
    TagMode
    -0.52
     bedrag
    -0.51
    POSITIVE LOGITS
    kaw
    0.38
    piecze
    0.33
     Zeich
    0.33
     Lehr
    0.33
     Receiver
    0.31
    情
    0.31
     will
    0.31
     marks
    0.31
    Printf
    0.30
     commun
    0.30
    Activations Density 0.291%

    No Known Activations