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. 57281
    Prev
    Next
    INDEX
    Explanations

    numerical data related to measurement and ratios

    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
    OGND
    -0.70
    parsedMessage
    -0.63
     '\\;'
    -0.62
     Paglinawan
    -0.61
     الرياضيه
    -0.61
    MessageOf
    -0.60
     disambiguazione
    -0.60
    isContained
    -0.59
    IndentedString
    -0.59
     Administrativna
    -0.58
    POSITIVE LOGITS
    /******/
    0.35
    ngOnDestroy
    0.33
     serius
    0.31
     okhttp
    0.31
     plais
    0.29
    rąg
    0.29
    clerview
    0.28
     obno
    0.27
     escala
    0.27
    /")
    0.27
    Activations Density 0.165%

    No Known Activations