© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31796
    Prev
    Next
    INDEX
    Explanations

    keywords related to markets and events, specifically food-related ones

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

    markets and stalls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    acuzzi
    -0.67
     phòng
    -0.66
    SourceChecksum
    -0.65
     Suite
    -0.55
     Hotels
    -0.55
    perty
    -0.53
     Suites
    -0.52
     Hoteles
    -0.52
    suites
    -0.52
    suite
    -0.52
    POSITIVE LOGITS
     stalls
    0.76
     stall
    0.73
     vendors
    0.71
     feira
    0.69
     Vendors
    0.68
    攤
    0.67
     Market
    0.67
     market
    0.65
    webElementXpaths
    0.65
     mercados
    0.65
    Activations Density 0.038%

    No Known Activations