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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8817
    Prev
    Next
    INDEX
    Explanations

    references to clothing items and their characteristics

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

    before/after "shirt"

    np_acts-logits-general · gemini-2.0-flash

    shirts and t-shirts

    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
    WarningLevel
    -0.63
    GEBURTS
    -0.61
     GenerationType
    -0.58
     decorativas
    -0.55
     kasarigan
    -0.54
     Вікі
    -0.50
    
    -0.48
    Karriere
    -0.46
    AsUp
    -0.46
    ResponseWriter
    -0.45
    POSITIVE LOGITS
     shirts
    1.13
     shirt
    1.07
     Shirts
    1.03
     Shirt
    0.99
    shirt
    0.91
    shirts
    0.90
     sweatshirt
    0.89
    hirts
    0.88
    hirt
    0.87
    Shirt
    0.84
    Activations Density 0.074%

    No Known Activations