© 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. 6505
    Prev
    Next
    INDEX
    Explanations

    regular expressions that match a specific pattern

    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
    Autoritní
    -0.70
    )['
    -0.67
    twimg
    -0.62
    ichtlich
    -0.62
     ©️
    -0.62
    ')['
    -0.60
    OGND
    -0.59
    reciated
    -0.59
    igil
    -0.59
     cherchés
    -0.57
    POSITIVE LOGITS
     énergé
    0.65
     sogno
    0.64
    LEncoder
    0.63
     giudi
    0.62
    writerow
    0.60
    four
    0.60
     Efq
    0.59
    +:+
    0.58
    RegistryLite
    0.58
    del
    0.56
    Activations Density 0.038%

    No Known Activations