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. 22-GEMMASCOPE-RES-16K
    6. 13042
    Prev
    Next
    INDEX
    Explanations

    rules and principles related to proper etiquette and social conduct

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

    Etiquette, manners, and professional behavior

    np_acts-logits-general · gemini-2.0-flash

    respectful behavior and etiquette

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.75
    ReusableCell
    -0.56
    StoryboardSegue
    -0.55
     peindre
    -0.55
    clare
    -0.54
    STIC
    -0.52
    diag
    -0.51
     aveug
    -0.51
    wnia
    -0.50
    apimachinery
    -0.50
    POSITIVE LOGITS
     respectful
    1.69
     respect
    1.63
     Respect
    1.61
     etiquette
    1.60
    respect
    1.60
     polite
    1.59
    Respect
    1.58
     manners
    1.51
     RESPECT
    1.45
     courteous
    1.42
    Activations Density 0.474%

    No Known Activations