© 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. 4508
    Prev
    Next
    INDEX
    Explanations

    references to academic and research credentials, including details about papers, theses, and author acknowledgments

    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
    Personensuche
    -0.99
    archiviato
    -0.91
    expandindo
    -0.90
    AndEndTag
    -0.86
    phosa
    -0.86
    HtmlAttribute
    -0.85
    '},
    -0.84
    )");
    -0.82
     оригіналу
    -0.81
     */
    -0.81
    POSITIVE LOGITS
     investigadores
    0.54
    论文
    0.48
     researchers
    0.46
     acadé
    0.45
     saan
    0.45
     Dissertation
    0.45
     dissertation
    0.45
    論文
    0.45
     doctoral
    0.45
    defineProperty
    0.44
    Activations Density 1.203%

    No Known Activations