© 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. 6-GEMMASCOPE-RES-16K
    11. 15608
    Prev
    Next
    INDEX
    Explanations

    phrases expressing perspective or opinion

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Couleur
    -0.67
    AsUp
    -0.66
     MediatR
    -0.64
    Шаг
    -0.60
    CodeDom
    -0.60
    dropIfExists
    -0.60
     sniffed
    -0.57
    autogui
    -0.54
     вдруг
    -0.53
     पता
    -0.52
    POSITIVE LOGITS
    可以说
    0.81
    ofern
    0.71
    程度上
    0.68
     sense
    0.66
     Extent
    0.64
    UnitTesting
    0.64
    kheim
    0.60
    OfWork
    0.60
     extent
    0.59
    揄
    0.59
    Activations Density 0.214%

    No Known Activations