© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16233
    Prev
    Next
    INDEX
    Explanations

    ingredients and components of food dishes, particularly those containing cheese and meat

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

    Comes before ingredients/toppings

    np_acts-logits-general · gemini-2.0-flash

    ingredients and accompaniments

    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
    didSet
    -0.63
     AssemblyTitle
    -0.61
     Hidup
    -0.55
     Kite
    -0.55
     الدولى
    -0.55
     oldValue
    -0.53
    ecma
    -0.53
     pior
    -0.52
     lemonade
    -0.51
     Tisch
    -0.51
    POSITIVE LOGITS
     topping
    0.73
     topped
    0.72
     layers
    0.68
     toppings
    0.64
     fillings
    0.63
     onions
    0.63
    $_['
    0.61
     filling
    0.61
    Hochspringen
    0.59
    phazard
    0.59
    Activations Density 0.095%

    No Known Activations