© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8148
    Prev
    Next
    INDEX
    Explanations

    references to specific musical works and authorship in compositions

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

    after commas, quotes, and apostrophes

    np_acts-logits-general · gemini-2.0-flash

    titles of books and artworks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    WriteBarrier
    -0.57
     Longfellow
    -0.51
     Ibsen
    -0.49
    XDECREF
    -0.49
    estros
    -0.48
     speciali
    -0.46
    Tradition
    -0.45
     onOptions
    -0.45
     Chaucer
    -0.44
    دانشنامهٔ
    -0.44
    POSITIVE LOGITS
    はじめに
    0.66
    ratulations
    0.65
    atise
    0.63
    ècie
    0.60
    ائص
    0.57
     الأربع
    0.56
    ModelAdmin
    0.56
    annten
    0.56
    pyplot
    0.55
    __':
    0.55
    Activations Density 0.135%

    No Known Activations