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. 4522
    Prev
    Next
    INDEX
    Explanations

    discourse concerning evaluations and critiques

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

    Appearing before "of" or a comma after "Review"

    np_acts-logits-general · gemini-2.0-flash

    academic or software reviews

    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
    Искәрмәләр
    -0.76
    Ārējās
    -0.67
     للمعارف
    -0.66
    EndGlobalSection
    -0.61
    odils
    -0.60
    struzioni
    -0.59
     getY
    -0.58
    🤣🤣
    -0.58
    друг
    -0.57
     imagePath
    -0.57
    POSITIVE LOGITS
    PhysRev
    0.98
     Reviews
    0.86
    Reviews
    0.83
     REVIEWS
    0.81
     reviews
    0.76
     Review
    0.70
    REVIEW
    0.69
     REVIEW
    0.68
    Portale
    0.64
    reviews
    0.63
    Activations Density 0.080%

    No Known Activations