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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1228
    Prev
    Next
    INDEX
    Explanations

    instances of respect and regard in interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hadid
    -0.52
    allax
    -0.52
     الميل
    -0.49
    FunctionType
    -0.48
    -------------</
    -0.48
     tendon
    -0.47
     Blob
    -0.47
    otheek
    -0.46
    kovich
    -0.46
    หวัด
    -0.46
    POSITIVE LOGITS
    Respect
    1.59
     Respect
    1.55
     respect
    1.50
    respect
    1.48
     respectful
    1.41
     respected
    1.40
     respek
    1.38
     respecting
    1.37
     RESPECT
    1.34
     respects
    1.32
    Activations Density 0.290%

    No Known Activations