© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10815
    Prev
    Next
    INDEX
    Explanations

    symbols and formatting related to code and programming structures

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

    structural markup and formatting characters like brackets, parentheses, and punctuation that delineate code or document sections.

    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
    SBATCH
    -0.56
    хьтан
    -0.54
    rungsseite
    -0.54
    \{\\
    -0.50
    HtmlAttribute
    -0.49
    matchCondition
    -0.48
    TokenNameDOT
    -0.48
    IsContent
    -0.47
    脚注の使い方
    -0.47
     """",
    -0.47
    POSITIVE LOGITS
     виправивши
    0.50
    neté
    0.48
    tagHelperRunner
    0.45
    expandindo
    0.43
    serviceWorker
    0.40
    XtraEditors
    0.39
    RTEE
    0.36
    IGraphics
    0.36
    gyz
    0.36
    tabular
    0.36
    Activations Density 0.798%

    No Known Activations