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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16192
    Prev
    Next
    INDEX
    Explanations

    references to dining experiences and restaurant etiquette

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

    before or related to "date" or "meal"

    np_acts-logits-general · gemini-2.0-flash

    social dates and meals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
    Архівовано
    -0.59
     الرياضيه
    -0.57
    Personendaten
    -0.57
     Normdatei
    -0.55
     Lightboxes
    -0.54
    كويكب
    -0.54
    Parcelize
    -0.52
    \{\\
    -0.52
    ftagPool
    -0.49
    سطس
    -0.49
    POSITIVE LOGITS
     outing
    1.07
     outings
    0.93
     date
    0.84
     lunch
    0.75
     dates
    0.71
     brunch
    0.70
     dinner
    0.69
     hangout
    0.68
     weekend
    0.68
    Date
    0.67
    Activations Density 0.148%

    No Known Activations