© 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. 11-GEMMASCOPE-RES-16K
    11. 9197
    Prev
    Next
    INDEX
    Explanations

    references to shadows in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ItemBackground
    -1.08
     propOrder
    -1.04
     referenties
    -0.94
    ReusableCell
    -0.93
     Levine
    -0.89
    ibouti
    -0.87
    Mane
    -0.87
    mogorov
    -0.86
    Abitanti
    -0.85
    BERGER
    -0.85
    POSITIVE LOGITS
    ec
    0.89
     Shadow
    0.86
    Shadow
    0.77
     Ec
    0.73
     éc
    0.73
    dou
    0.71
    zet
    0.71
     shadow
    0.71
    awtextra
    0.71
     Boek
    0.70
    Activations Density 0.458%

    No Known Activations