© 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. 0-GEMMASCOPE-RES-65K
    11. 6610
    Prev
    Next
    INDEX
    Explanations

    phrases related to tuning and styling, particularly in the context of vehicles or fashion

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    InjectAttribute
    -0.87
    Personensuche
    -0.76
     חיצוניים
    -0.71
     صوتيه
    -0.68
     betweenstory
    -0.66
    AddTagHelper
    -0.63
    tagHelperRunner
    -0.62
    iNdEx
    -0.62
     @"/
    -0.58
    ChildScrollView
    -0.58
    POSITIVE LOGITS
     الاطلاع
    0.77
     étranger
    0.71
     Styling
    0.68
     annuel
    0.68
     isolado
    0.66
     privée
    0.66
     asmen
    0.65
     convert
    0.64
     mères
    0.63
     medži
    0.63
    Activations Density 0.034%

    No Known Activations