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. 3198
    Prev
    Next
    INDEX
    Explanations

    references to cheese-based items or dishes

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

    Presence of "cheese" or types of cheese

    np_acts-logits-general · gemini-2.0-flash

    cheese and dairy

    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
    URLException
    -0.60
    kian
    -0.56
     Beagle
    -0.54
    WebVitals
    -0.52
    mingbird
    -0.52
     Malaria
    -0.52
     Carvalho
    -0.51
    SqlQuery
    -0.49
    TintMode
    -0.49
     hemat
    -0.48
    POSITIVE LOGITS
     cheese
    1.75
     Cheese
    1.57
    Cheese
    1.47
    cheese
    1.42
     cheeses
    1.39
    🧀
    1.20
     dairy
    1.18
     cheddar
    1.13
     milk
    1.13
    Dairy
    1.04
    Activations Density 0.148%

    No Known Activations