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. 9397
    Prev
    Next
    INDEX
    Explanations

    structured data formats and their components

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

    Code, math, or technical language

    np_acts-logits-general · gemini-2.0-flash

    code punctuation or symbols

    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
     pungkasnya
    -0.43
    aryti
    -0.43
     simply
    -0.41
    %@",
    -0.40
    tetten
    -0.39
     apapun
    -0.39
    ್ದ
    -0.39
     Leal
    -0.38
    hæng
    -0.38
     Segal
    -0.38
    POSITIVE LOGITS
     ویکی‌پدی
    1.10
     nakalista
    1.06
    WithIOException
    1.01
     disambiguazione
    0.95
     EconPapers
    0.85
    SharedCtor
    0.83
     propOrder
    0.83
    GEBURTSDATUM
    0.83
     мәкал
    0.82
    MigrationBuilder
    0.81
    Activations Density 0.831%

    No Known Activations