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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14119
    Prev
    Next
    INDEX
    Explanations

    text that cites legal references and sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     consistent
    -0.86
     consistency
    -0.82
     consistently
    -0.66
     Consistent
    -0.65
     uniform
    -0.64
    consistent
    -0.63
    Consistent
    -0.62
    Consistency
    -0.60
    consistency
    -0.60
     Consistency
    -0.60
    POSITIVE LOGITS
     page
    1.67
     p
    1.50
     pp
    1.46
     pages
    1.44
    page
    1.37
     pg
    1.36
     Page
    1.26
     pág
    1.26
    pages
    1.21
     página
    1.19
    Activations Density 1.210%

    No Known Activations