© 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. 54946
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hush" and its variations as well as other expressions of softness or quietness

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

    hush money, hushpuppy, blush

    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
     يتيمه
    -0.56
    plotly
    -0.55
    (©
    -0.53
     entrain
    -0.53
     ſp
    -0.52
    fara
    -0.51
     Ethyl
    -0.50
    pital
    -0.49
     Mandala
    -0.49
     Teg
    -0.49
    POSITIVE LOGITS
     aunque
    0.93
    aunque
    0.88
     Aunque
    0.81
    Aunque
    0.80
     meski
    0.68
    Pues
    0.62
    不过
    0.59
    Meski
    0.59
     choć
    0.57
     pues
    0.56
    Activations Density 0.003%

    No Known Activations