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. 11841
    Prev
    Next
    INDEX
    Explanations

    variations of the word "sto" in different contexts

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

    starting with "Sto" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    words starting with "Sto"

    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
    الإنجليزية
    -0.87
     chi̍t
    -0.85
     שוליים
    -0.78
     EconPapers
    -0.77
     Réponses
    -0.72
    DockStyle
    -0.71
    ItemBackground
    -0.69
     חיצוניים
    -0.68
    مصادر
    -0.68
     تضيفلها
    -0.67
    POSITIVE LOGITS
     Sto
    0.93
     sto
    0.80
    Sto
    0.79
     STO
    0.63
     Stomp
    0.53
     Stoll
    0.50
    Сто
    0.49
    sto
    0.49
     Stor
    0.47
     STORE
    0.44
    Activations Density 0.069%

    No Known Activations