© 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. 8134
    Prev
    Next
    INDEX
    Explanations

    function-related operations and methods in programming.

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

    JavaScript code snippets involving specific methods and syntax patterns.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    code patterns related to visiting or traversing data structures, particularly in the context of serialization or parsing.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Protobuf-related code

    np_acts-logits-general · gemini-2.0-flash

    field declarations

    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
     religieuses
    -0.67
    URLException
    -0.66
     Drapeau
    -0.66
     Theſe
    -0.63
    ndy
    -0.63
    raszamy
    -0.62
    ubourg
    -0.62
     Wiktionnaire
    -0.61
     démocr
    -0.61
    Przypisy
    -0.60
    POSITIVE LOGITS
    Autoritní
    0.67
    ConstraintMaker
    0.56
     the
    0.55
    angliski
    0.55
     autorytatywna
    0.54
     protoimpl
    0.53
    InjectAttribute
    0.48
    SuppressMessage
    0.48
     either
    0.46
    こちらも
    0.45
    Activations Density 0.033%

    No Known Activations