© 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. 14929
    Prev
    Next
    INDEX
    Explanations

    references and citations within a structured document

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

    Text appearing in "section" headers

    np_acts-logits-general · gemini-2.0-flash

    section headings

    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
     reaſon
    -0.82
     AssemblyCulture
    -0.80
    ConstraintMaker
    -0.78
     myſelf
    -0.76
     NDEBUG
    -0.73
     itſelf
    -0.73
     leſs
    -0.72
     وتسجيلات
    -0.71
     dieß
    -0.71
    SharedCtor
    -0.70
    POSITIVE LOGITS
    wel
    0.51
    section
    0.51
     Introduction
    0.51
     se
    0.49
    Introduction
    0.49
    把手
    0.49
     ø
    0.45
    <eos>
    0.44
     W
    0.44
     Wer
    0.44
    Activations Density 0.154%

    No Known Activations