© 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. 27896
    Prev
    Next
    INDEX
    Explanations

    action verbs related to responsibilities and tasks in nursing or healthcare roles

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

    relationships or budget

    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
     snippetHide
    -0.75
     utafitiHapana
    -0.68
     kaynağından
    -0.67
     otomatig
    -0.66
     autorytatywna
    -0.66
    haikusbot
    -0.59
    sizeCache
    -0.57
     ویکی‌پدی
    -0.56
    InjectAttribute
    -0.56
    Tembelea
    -0.54
    POSITIVE LOGITS
    riwal
    0.50
    GetAxis
    0.42
     cozinha
    0.40
    AnchorTagHelper
    0.39
    exprimer
    0.39
     arbejde
    0.39
     žem
    0.38
     koszulka
    0.38
     Escolar
    0.38
     others
    0.36
    Activations Density 0.071%

    No Known Activations