© 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. 955
    Prev
    Next
    INDEX
    Explanations

    the beginning of sections in the document, signified by specific starting tokens

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

    Code-related syntax or comments

    np_acts-logits-general · gemini-2.0-flash

    code structure

    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
    IUrlHelper
    -0.86
    اریخ
    -0.82
     تانيه
    -0.80
     betweenstory
    -0.77
     estekak
    -0.76
    parsedMessage
    -0.76
    Diweddarwch
    -0.68
    رشف
    -0.65
    LookAnd
    -0.64
    Tembelea
    -0.62
    POSITIVE LOGITS
    धारण
    0.54
    <eos>
    0.52
    closePath
    0.49
    DoubleQuotes
    0.48
    [::-
    0.48
    ExecuteNonQuery
    0.47
    了吧
    0.46
    ↵↵↵↵
    0.46
    ↵↵↵↵↵
    0.46
    antana
    0.46
    Activations Density 0.390%

    No Known Activations