© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 67948
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements in structured documents

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

    data types and syntax

    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
     kasarigan
    -0.93
    rungsseite
    -0.78
    addCriterion
    -0.75
    GEBURTSDATUM
    -0.74
     autorytatywna
    -0.73
     ब्रेकडाउन
    -0.72
    NameInMap
    -0.71
    IndentedString
    -0.69
     transfieras
    -0.69
     ErrIntOverflow
    -0.69
    POSITIVE LOGITS
     similarly
    0.53
     Similarly
    0.52
    同样
    0.50
    Similarly
    0.50
     likewise
    0.50
     szint
    0.50
     ebenfalls
    0.48
    同樣
    0.46
    By
    0.46
     yine
    0.45
    Activations Density 0.044%

    No Known Activations