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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7342
    Prev
    Next
    INDEX
    Explanations

    sequences of values in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    webElementXpaths
    -0.80
    Tembelea
    -0.69
     PeEnEo
    -0.67
     AssemblyCulture
    -0.67
    UrlResolution
    -0.65
    ViewImports
    -0.63
     nonUne
    -0.61
     nahilalakip
    -0.61
    IUrlHelper
    -0.60
    TagMode
    -0.58
    POSITIVE LOGITS
     priori
    0.35
     pères
    0.35
    dians
    0.34
    zake
    0.34
    XmlAccessType
    0.34
     namelijk
    0.34
     Arturo
    0.34
    sign
    0.34
    line
    0.34
    art
    0.33
    Activations Density 0.022%

    No Known Activations