© 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. 6414
    Prev
    Next
    INDEX
    Explanations

    sequences or structures indicative of categorical data or items

    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
     iſt
    -2.13
     $_"
    -2.13
     ―――――
    -2.09
     Efq
    -2.03
     myſelf
    -2.02
     Anſ
    -2.00
     Majefty
    -1.98
     Reſ
    -1.97
    ſelf
    -1.96
     itſelf
    -1.95
    POSITIVE LOGITS
    ↵↵
    4.28
    ↵
    3.05
    ↵↵↵
    2.72
    <eos>
    2.50
    ↵↵↵↵
    2.44
    ↵↵↵↵↵
    2.20
    ↵↵↵↵↵↵
    1.95
    <h2>
    1.89
    ↵↵↵↵↵↵↵
    1.70
    ↵↵↵↵↵↵↵↵
    1.70
    Activations Density 1.013%

    No Known Activations