© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 27815
    Prev
    Next
    INDEX
    Explanations

    conditional phrases or statements expressing preference or opinion

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    whether or not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    elemField
    -0.60
    DoubleQuotes
    -0.42
     digital
    -0.39
     Hild
    -0.39
    锈钢
    -0.38
    Bronnen
    -0.36
    Nonnull
    -0.36
     wikipagina
    -0.36
     competitive
    -0.36
    انيف
    -0.36
    POSITIVE LOGITS
    twimg
    0.51
     Winaray
    0.41
    /**
    0.39
    AccessorTable
    0.39
     gand
    0.38
    ])[
    0.38
    engagent
    0.37
    addPreferredGap
    0.37
    +#+
    0.37
     متعلقه
    0.37
    Activations Density 0.102%

    No Known Activations