© 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. 13564
    Prev
    Next
    INDEX
    Explanations

    mentions of spas and related recreational activities

    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
     SEDS
    -0.54
    okovic
    -0.51
    pats
    -0.51
    etCode
    -0.51
     mus
    -0.51
     Dep
    -0.50
     ré
    -0.50
     Edmonds
    -0.49
     Magnus
    -0.49
    umenical
    -0.49
    POSITIVE LOGITS
    SourceChecksum
    0.87
     flares
    0.70
     blasting
    0.69
     rallies
    0.66
    tonsoft
    0.66
    reportWebVitals
    0.64
     صوتيه
    0.63
    litter
    0.62
     Ewig
    0.62
     blasted
    0.61
    Activations Density 0.074%

    No Known Activations