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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3952
    Prev
    Next
    INDEX
    Explanations

    elements related to vibrant culinary and cultural experiences

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

    Describing locations, markets, or dishes

    np_acts-logits-general · gemini-2.0-flash

    food markets and dishes

    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
     etc
    -0.52
     jöv
    -0.50
    在我们
    -0.47
     $\
    -0.45
     Estaba
    -0.45
     "<?
    -0.44
     brutto
    -0.44
     bisherigen
    -0.43
     estava
    -0.43
    esModule
    -0.43
    POSITIVE LOGITS
     locals
    0.91
    noons
    0.85
     youll
    0.79
     boasts
    0.78
    msgTypes
    0.77
     famously
    0.75
     famed
    0.72
     boasting
    0.72
     unknownFields
    0.72
     impressively
    0.70
    Activations Density 0.215%

    No Known Activations