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

    Neuronpedia

    Jacobian LensNEW
    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. 71833
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical identifiers or codes

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

    addresses and affiliations

    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
     indígen
    -0.84
     MainAxisSize
    -0.78
     CURIAM
    -0.77
    transQ
    -0.76
     ddelwed
    -0.75
     dieſer
    -0.71
    TokenNameLBRACE
    -0.70
     laſſen
    -0.70
     zuſammen
    -0.70
    plash
    -0.69
    POSITIVE LOGITS
     -
    0.90
    -
    0.87
    >−</
    0.71
    >-</
    0.69
    //-
    0.66
    -\
    0.63
    }-\
    0.63
    –
    0.60
    ）-
    0.60
    *
    0.59
    Activations Density 0.053%

    No Known Activations