Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-GEMMASCOPE-RES-16K
    6. 14730
    Prev
    Next
    INDEX
    Explanations

    instances of the word "respect" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ดย
    -0.73
     []:
    -0.72
    illou
    -0.71
     Arrondissement
    -0.70
     aastal
    -0.70
    OGND
    -0.69
    unif
    -0.67
    Chham
    -0.67
    注定
    -0.66
    uldron
    -0.65
    POSITIVE LOGITS
     Respect
    1.80
    Respect
    1.76
     respect
    1.76
     RESPECT
    1.67
    respect
    1.61
     respects
    1.49
     respectful
    1.40
     respecting
    1.34
     respek
    1.33
     respected
    1.33
    Activations Density 0.077%

    No Known Activations