© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 8323
    Prev
    Next
    INDEX
    Explanations

    references to home appliance services and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.37
    roli
    -0.36
    OCCURRED
    -0.36
    ariConfig
    -0.35
    izr
    -0.35
     SqlParameter
    -0.35
    ORDIN
    -0.35
    nloa
    -0.35
    iscope
    -0.34
    例文
    -0.34
    POSITIVE LOGITS
     brands
    3.30
     brand
    3.30
    brand
    2.91
    brands
    2.80
     Brand
    2.80
    Brand
    2.77
     Brands
    2.70
     BRAND
    2.69
    Brands
    2.67
    品牌
    2.63
    Activations Density 0.281%

    No Known Activations