Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9296
    Prev
    Next
    INDEX
    Explanations

    references to code elements and documentation within programming contexts

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

    structural markup and formatting elements like brackets, backslashes, and LaTeX commands.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.77
    PerformLayout
    -0.77
    +#+
    -0.76
    IsContent
    -0.75
    sizeCache
    -0.73
    istoitu
    -0.73
    HtmlAttribute
    -0.70
     queſta
    -0.69
    DockStyle
    -0.69
    GEBURTS
    -0.68
    POSITIVE LOGITS
    section
    0.55
    *{
    0.44
    <em>
    0.35
    <u>
    0.34
    <i>
    0.34
    {
    0.34
    Section
    0.30
    <b>
    0.29
    方
    0.28
     ordres
    0.28
    Activations Density 0.003%

    No Known Activations