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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13834
    Prev
    Next
    INDEX
    Explanations

    guidelines and etiquette related to dining behavior

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

    Dining etiquette and utensils

    np_acts-logits-general · gemini-2.0-flash

    eating utensils and plates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     combineReducers
    -0.79
    存于互联网档案馆
    -0.76
    AutoScaleMode
    -0.67
    RegressionTest
    -0.65
     فريبيس
    -0.64
     intptr
    -0.63
    
    -0.58
    出版年
    -0.55
    ocardium
    -0.52
     AssemblyCulture
    -0.52
    POSITIVE LOGITS
     plate
    1.00
     chopsticks
    0.99
     spoon
    0.94
     plates
    0.91
     fork
    0.89
     eating
    0.89
     cutlery
    0.88
     spoonful
    0.87
    Plate
    0.82
     mouthful
    0.82
    Activations Density 0.160%

    No Known Activations