© 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. 94076
    Prev
    Next
    INDEX
    Explanations

    reviews discussing the comfort and fit of sports bras

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

    evaluative language and phrases

    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
    parsedMessage
    -0.83
    GEBURTSDATUM
    -0.67
    findpost
    -0.63
    __':
    -0.57
     increí
    -0.55
    TagMode
    -0.54
    clerView
    -0.53
     ſich
    -0.53
    arangay
    -0.53
     snippetHide
    -0.52
    POSITIVE LOGITS
    Pyx
    0.37
    JsonFormat
    0.32
     yön
    0.30
    glClear
    0.30
    Lieu
    0.29
    endroit
    0.29
     corrid
    0.28
     Calab
    0.28
     Hy
    0.27
     gelişti
    0.27
    Activations Density 0.049%

    No Known Activations