© 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. 6050
    Prev
    Next
    INDEX
    Explanations

    elements related to food preparation and snack options

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

    food and snack items, especially in contexts describing culinary preparations or food consumption.

    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
    esgue
    -0.49
     cooking
    -0.45
     cocinar
    -0.44
     cooks
    -0.44
     kuah
    -0.43
     restoran
    -0.43
     cocin
    -0.43
     Cooker
    -0.42
     cook
    -0.42
     ویکی‌پدی
    -0.42
    POSITIVE LOGITS
     snack
    1.12
     snacks
    1.11
     Snacks
    0.94
    snack
    0.93
     Snack
    0.90
    Snacks
    0.89
    Snack
    0.79
     nib
    0.75
     munch
    0.71
    零食
    0.68
    Activations Density 0.126%

    No Known Activations