© 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. 31-GEMMASCOPE-RES-16K
    6. 15899
    Prev
    Next
    INDEX
    Explanations

    specific formatting elements and structure in written documents, like lists and sections

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

    bulleted or numbered lists with colons introducing the list items.

    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
    tagHelperRunner
    -0.75
    ⟬
    -0.71
    parsedMessage
    -0.66
     Numerade
    -0.66
    AndEndTag
    -0.63
    Autoritní
    -0.63
     propOrder
    -0.62
    InSection
    -0.61
    出版年
    -0.61
    (©
    -0.60
    POSITIVE LOGITS
     •
    1.30
    •
    1.25
    ・
    0.98
     -
    0.94
     *
    0.90
     ·
    0.87
     ・
    0.86
    ·
    0.86
    ●
    0.83
    *
    0.82
    Activations Density 0.616%

    No Known Activations