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. 7422
    Prev
    Next
    INDEX
    Explanations

    LaTeX code related to graphical elements and their styling parameters

    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
     inoxid
    -0.49
     teil
    -0.44
    genza
    -0.42
    RenderAtEndOf
    -0.42
    Nullable
    -0.41
     fini
    -0.41
     kidding
    -0.40
    Vie
    -0.40
     forKey
    -0.40
    ForResult
    -0.40
    POSITIVE LOGITS
     <=",
    0.86
     للاسماء
    0.78
     EconPapers
    0.72
    principalColumn
    0.68
     Normdatei
    0.66
    aarrggbb
    0.64
     bookmark
    0.63
     bookmarks
    0.62
    ThroughAttribute
    0.62
    ChromeDriver
    0.61
    Activations Density 0.294%

    No Known Activations