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. 77223
    Prev
    Next
    INDEX
    Explanations

    keywords and syntax elements related to programming functions and templates

    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
    tanleria
    -0.43
    writeFieldEnd
    -0.38
    toprule
    -0.36
    mages
    -0.35
     hunde
    -0.34
     käyt
    -0.33
    enumi
    -0.33
     niega
    -0.33
    เกิน
    -0.33
     määrä
    -0.33
    POSITIVE LOGITS
    AccessorTable
    0.74
     препратки
    0.59
     informée
    0.57
     يتيمه
    0.47
     jdbcTemplate
    0.45
    MLLoader
    0.45
    invokeLater
    0.44
    AnchorTagHelper
    0.43
    lenovo
    0.43
    yntaxException
    0.43
    Activations Density 0.017%

    No Known Activations