Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113575
    Prev
    Next
    INDEX
    Explanations

    names of cities and geographical locations

    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
     AssemblyCulture
    -0.73
    centralwidget
    -0.65
     ujednoznacz
    -0.63
    featureID
    -0.61
     архивлан
    -0.59
    TagMode
    -0.59
     jspb
    -0.59
     оригіналу
    -0.57
    verifyException
    -0.57
     RISERVATA
    -0.56
    POSITIVE LOGITS
    Portály
    0.38
     Palembang
    0.31
    APORE
    0.31
     Hoof
    0.30
     investigators
    0.30
    bieter
    0.29
     roue
    0.29
    Frankreich
    0.28
     brû
    0.28
     pinulongan
    0.28
    Activations Density 0.037%

    No Known Activations