© 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. 6358
    Prev
    Next
    INDEX
    Explanations

    references to healthcare professionals and mentions of towns

    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
     ainfi
    -1.09
     myſelf
    -1.06
     Jefus
    -1.04
     Monfieur
    -1.02
     pitié
    -0.99
     itſelf
    -0.98
     cdti
    -0.95
     feroit
    -0.93
     auffi
    -0.93
     crdi
    -0.93
    POSITIVE LOGITS
     professional
    0.76
     personal
    0.64
    .
    0.59
     go
    0.59
     sk
    0.59
    town
    0.57
     pro
    0.56
     include
    0.56
     under
    0.55
     plus
    0.55
    Activations Density 0.047%

    No Known Activations