© 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. 20-GEMMASCOPE-RES-131K
    11. 62797
    Prev
    Next
    INDEX
    Explanations

    references to shopping and inventory organization, particularly in a grocery context

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

    storage shelves and containers

    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
    Negative Logits
    SharedCtor
    -0.52
     Administrativna
    -0.46
    aarrggbb
    -0.45
     sesión
    -0.39
    ViewImports
    -0.38
    prüche
    -0.37
     reconn
    -0.37
    protoc
    -0.36
    woners
    -0.35
     girasol
    -0.35
    POSITIVE LOGITS
     shelves
    0.66
     aisles
    0.59
     shelving
    0.59
     Shelves
    0.56
     Shelf
    0.51
     shelf
    0.50
     catalogs
    0.50
     aisle
    0.49
     racks
    0.49
     bookcase
    0.47
    Activations Density 0.014%

    No Known Activations