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. 12348
    Prev
    Next
    INDEX
    Explanations

    references to medical terms and jargon

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

    Punctuation, symbols, and equation-related tokens

    np_acts-logits-general · gemini-2.0-flash

    any specific whatsoever

    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
    adaptiveStyles
    -0.80
    MigrationBuilder
    -0.77
     AssemblyCulture
    -0.76
     ExecuteAsync
    -0.73
    contentLoaded
    -0.72
    AddTagHelper
    -0.71
    Manbalar
    -0.71
    PerformLayout
    -0.70
     ***!
    -0.68
     disambiguazione
    -0.65
    POSITIVE LOGITS
     etc
    0.89
     quelcon
    0.83
     quelconque
    0.82
     itp
    0.78
     whatever
    0.73
     whichever
    0.72
     usw
    0.69
    etc
    0.66
    什么的
    0.64
    之类的
    0.64
    Activations Density 0.400%

    No Known Activations