© 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 EvalsExportsinterp-engineNEWAPI 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. 66554
    Prev
    Next
    INDEX
    Explanations

    terms related to exit, removal, or exclusion

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

    Aus, aus, Aus, Ausland, auscultated, Ausubel, Ausmus

    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
     ainfi
    -1.02
     plufieurs
    -0.90
    parsedMessage
    -0.83
     dezelve
    -0.82
     vectorielle
    -0.82
     zoude
    -0.77
     feroit
    -0.75
     enfans
    -0.74
     mauva
    -0.74
     dignité
    -0.73
    POSITIVE LOGITS
     Aus
    0.96
     aus
    0.85
    Aus
    0.84
     AUS
    0.84
     OUT
    0.83
    Out
    0.80
     Out
    0.79
     out
    0.77
    out
    0.73
    OUT
    0.70
    Activations Density 0.002%

    No Known Activations