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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8140
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions and demographic factors related to nutrition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ration
    -0.39
     grade
    -0.39
     signal
    -0.39
     ویکی‌پدیا
    -0.38
     ride
    -0.37
     shop
    -0.36
    Халык
    -0.36
     patrol
    -0.36
     stalk
    -0.36
     Life
    -0.36
    POSITIVE LOGITS
     continents
    0.84
     Asia
    0.80
     continent
    0.71
    Asia
    0.71
     asiática
    0.70
    Asie
    0.70
    continent
    0.70
     Asie
    0.68
     Regionen
    0.66
    MigrationBuilder
    0.66
    Activations Density 0.049%

    No Known Activations