© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105510
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and jargon related to various fields such as finance, medicine, and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.62
    الحياه
    -0.58
    aarrggbb
    -0.57
     للاسماء
    -0.57
    HostException
    -0.56
    URLException
    -0.55
    kulu
    -0.54
     ujednoznacz
    -0.52
    __["
    -0.51
    Notae
    -0.51
    POSITIVE LOGITS
    apimachinery
    0.43
     nôtre
    0.40
    хьтан
    0.34
     consommate
    0.34
    lccn
    0.31
     Sénat
    0.30
     NSCoder
    0.30
     käytt
    0.29
     vôtre
    0.29
    VAO
    0.28
    Activations Density 0.076%

    No Known Activations