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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 33422
    Prev
    Next
    INDEX
    Explanations

    technical terms and constructs related to factories in programming or database contexts

    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
     defaultstate
    -0.50
     onOptions
    -0.46
     alſo
    -0.45
    HttpServlet
    -0.45
    헌
    -0.44
    batik
    -0.43
    醐
    -0.43
     ſtill
    -0.43
     ſmall
    -0.43
     contextLoads
    -0.43
    POSITIVE LOGITS
    Seeder
    0.51
    factories
    0.48
    ArgumentParser
    0.48
    Factories
    0.45
    GeneratedValue
    0.43
    factory
    0.43
     factory
    0.41
    RSpec
    0.41
    ător
    0.40
     fabrique
    0.40
    Activations Density 0.003%

    No Known Activations