© 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 - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 14503
    Prev
    Next
    INDEX
    Explanations

    keywords related to unique or special concepts, particularly those associated with sacredness, food, or specific types of products

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Caron
    -0.88
     Walpole
    -0.88
    tanleria
    -0.87
    ніципа
    -0.85
    ukone
    -0.83
    κίνη
    -0.83
     Scarborough
    -0.82
    хьтан
    -0.81
     raiſ
    -0.80
     itſelf
    -0.80
    POSITIVE LOGITS
     Ye
    0.97
     ye
    0.95
    ye
    0.89
    Ye
    0.81
    fro
    0.80
     Elder
    0.74
     fro
    0.73
    Fro
    0.69
     Fro
    0.69
     Bro
    0.69
    Activations Density 0.107%

    No Known Activations