© 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. 63322
    Prev
    Next
    INDEX
    Explanations

    the preposition "per" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    according to standards or requests

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    MultipartFile
    -0.39
     corredor
    -0.38
     seules
    -0.38
    RuleContext
    -0.36
     fabricantes
    -0.36
    trás
    -0.34
     оно
    -0.34
    它
    -0.33
     mús
    -0.33
     financiera
    -0.33
    POSITIVE LOGITS
    agaimana
    0.71
    __(/*!
    0.67
    VersionUID
    0.67
    omitempty
    0.63
    ibley
    0.60
    Kjelder
    0.59
    epam
    0.59
     kaarangay
    0.59
     հղումներ
    0.59
     مُعرِّف
    0.58
    Activations Density 0.004%

    No Known Activations