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. 10114
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

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

    "Thank you" followed by a polite continuation

    np_acts-logits-general · gemini-2.0-flash

    saying thank you

    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
     חיצוניים
    -0.64
    URLEncoder
    -0.61
     Италијани
    -0.60
    Siamo
    -0.57
     nakalista
    -0.56
    mişti
    -0.55
     useStyles
    -0.55
     kaynağından
    -0.53
    도록
    -0.53
     InputDecoration
    -0.52
    POSITIVE LOGITS
    ReusableCell
    0.78
     goodness
    0.69
     god
    0.64
    NOPQRST
    0.60
    !*\
    0.60
     heavens
    0.58
     Goodness
    0.55
     tank
    0.54
    god
    0.53
    staking
    0.52
    Activations Density 0.043%

    No Known Activations