© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13800
    Prev
    Next
    INDEX
    Explanations

    terms related to respect and treatment of people

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

    Follows "with" or "you"

    np_acts-logits-general · gemini-2.0-flash

    treat with dignity or ignorance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itures
    -0.50
    protoimpl
    -0.49
    śred
    -0.48
    ellan
    -0.47
     peindre
    -0.46
    codable
    -0.45
    cluse
    -0.45
    %\\
    -0.45
     RoutedEventArgs
    -0.45
    ecuted
    -0.45
    POSITIVE LOGITS
     respect
    2.14
     Respect
    1.95
    Respect
    1.89
    respect
    1.85
     respects
    1.72
     RESPECT
    1.69
     respectful
    1.62
     treat
    1.61
     treating
    1.60
     respecting
    1.58
    Activations Density 0.300%

    No Known Activations