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. 53859
    Prev
    Next
    INDEX
    Explanations

    quantitative data or statistics related to amounts or percentages

    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
     dsl
    -0.44
     GA
    -0.43
     css
    -0.41
     SC
    -0.39
     hamilton
    -0.39
     TB
    -0.39
     FA
    -0.39
     pr
    -0.39
     Avi
    -0.38
     RI
    -0.38
    POSITIVE LOGITS
     unicórnio
    0.79
     Wikiseite
    0.79
    majánló
    0.71
     ilustracja
    0.69
     normalidad
    0.67
     almohada
    0.66
     skupina
    0.66
     Económica
    0.66
     polaire
    0.66
    berdayakan
    0.66
    Activations Density 0.068%

    No Known Activations