© 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. 13416
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "top" and related terms that indicate ranking or position

    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
    脚注の使い方
    -0.90
    ProcessEvent
    -0.68
     ویکی‌پدیا
    -0.67
    InputTagHelper
    -0.66
    findpost
    -0.65
     EconPapers
    -0.65
     initWithFrame
    -0.64
    verwijspagina
    -0.64
    __*/
    -0.63
    principalColumn
    -0.61
    POSITIVE LOGITS
    $_['
    0.56
    ровала
    0.53
    liegenden
    0.52
     recevrez
    0.52
     Shenandoah
    0.52
    āju
    0.50
     nativa
    0.49
    Kary
    0.49
     상세
    0.48
    aruhi
    0.48
    Activations Density 0.068%

    No Known Activations