© 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. 11586
    Prev
    Next
    INDEX
    Explanations

    numerical references or citations in scientific texts

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

    Citations with numbers and parentheses

    np_acts-logits-general · gemini-2.0-flash

    digits following numbers or years

    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
     للمعارف
    -0.78
    tvguidetime
    -0.76
     متعلقه
    -0.73
     AssemblyTitle
    -0.70
     وتسجيلات
    -0.68
    ReusableCell
    -0.65
    CppMethod
    -0.65
     سكانية
    -0.64
    脚注の使い方
    -0.64
     consultato
    -0.63
    POSITIVE LOGITS
     Lu
    0.50
    出版年
    0.49
    settled
    0.49
    här
    0.47
    Lu
    0.44
     Lue
    0.44
     Luke
    0.43
     Ordnung
    0.43
     No
    0.42
     art
    0.42
    Activations Density 0.259%

    No Known Activations