© 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. 81565
    Prev
    Next
    INDEX
    Explanations

    elements of feedback or review assessments

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

    words before punctuation or connectors

    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
    ScopeManager
    -0.90
     sumpay
    -0.70
     للمعارف
    -0.69
     queſta
    -0.68
    +#+#
    -0.66
     ब्रेकडाउन
    -0.63
     typelib
    -0.62
     Autorizaciones
    -0.62
     ProtoMessage
    -0.61
     ddelwed
    -0.60
    POSITIVE LOGITS
    spunkt
    0.31
    !
    0.29
     honestly
    0.29
     buen
    0.29
    ズ
    0.28
     pendapat
    0.28
    djangoproject
    0.28
    整
    0.27
    other
    0.27
     söyle
    0.26
    Activations Density 0.005%

    No Known Activations