© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 694
    Prev
    Next
    INDEX
    Explanations

    various structural elements of documents, including punctuation, headers, and formatting

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

    dates, times, and numerical information in event announcements and procedural instructions.

    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
    ThroughAttribute
    -0.49
     nahilalakip
    -0.46
    раздо
    -0.45
    AndEndTag
    -0.44
    styleType
    -0.43
    SharedDtor
    -0.43
    EnableWeb
    -0.43
     مشين
    -0.41
    المشاركات
    -0.40
    */].
    -0.40
    POSITIVE LOGITS
     anyone
    0.84
     Anyone
    0.83
    Anyone
    0.79
     Individuals
    0.71
     individuals
    0.70
    anyone
    0.69
     participants
    0.66
     ANYONE
    0.66
     Individual
    0.66
     anybody
    0.65
    Activations Density 0.328%

    No Known Activations