© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 2220
    Prev
    Next
    INDEX
    Explanations

    segments of code or scripting elements in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     træ
    -0.38
    waniu
    -0.36
     [
    -0.35
    <eos>
    -0.35
    使
    -0.34
    以上
    -0.34
     tiks
    -0.32
     cờ
    -0.31
    atoto
    -0.31
    ся
    -0.31
    POSITIVE LOGITS
    SourceChecksum
    0.82
    HtmlAttribute
    0.77
    WriteLiteral
    0.75
    TagHelper
    0.73
    httphttps
    0.73
     Paglinawan
    0.72
    DoubleQuotes
    0.71
    AddHtmlAttribute
    0.68
    UrlResolution
    0.68
    AnchorTagHelper
    0.62
    Activations Density 0.004%

    No Known Activations