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. 16-GEMMASCOPE-RES-16K
    6. 12385
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concept descriptions, particularly those related to experimental setups or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions "in", "as", "for" followed by "the" or articles

    np_acts-logits-general · gemini-2.0-flash

    in the context of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.95
    ValueStyle
    -0.82
    :✨
    -0.80
    SaveChangesAsync
    -0.77
    webElementXpaths
    -0.77
    WebVitals
    -0.76
    ContentAlignment
    -0.74
     JpaRepository
    -0.69
     متعلقه
    -0.67
     AssemblyCulture
    -0.67
    POSITIVE LOGITS
     oleh
    0.69
     by
    0.66
     توسط
    0.48
     EconPapers
    0.48
     different
    0.47
     Cli
    0.47
     пользователем
    0.46
     cli
    0.46
     ребен
    0.45
     Blocks
    0.45
    Activations Density 0.668%

    No Known Activations