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. 4476
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "quick" and its variations

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

    "quick" or its variants

    np_acts-logits-general · gemini-2.0-flash

    quick or rapid followed by a noun

    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
     للاسماء
    -1.03
    WebElementEntity
    -0.67
     Riproduzione
    -0.66
    principalColumn
    -0.66
    ="#"><
    -0.63
    ثيق
    -0.62
    ɵɵelementStart
    -0.60
    kuuta
    -0.59
     חיצוניים
    -0.59
    __':
    
    -0.58
    POSITIVE LOGITS
     Quick
    0.92
    Quick
    0.89
     QUICK
    0.89
     quick
    0.88
     chóng
    0.86
    quick
    0.85
    Rapid
    0.82
    QUICK
    0.80
     rapide
    0.80
     Rapid
    0.77
    Activations Density 0.133%

    No Known Activations