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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10951
    Prev
    Next
    INDEX
    Explanations

    various forms of greetings and sign-offs in correspondence

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

    Formal email closings (Kind, Best, Sincerely, Regards)

    np_acts-logits-general · gemini-2.0-flash

    polite email or letter closings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.85
     Мексичка
    -0.80
    ReusableCell
    -0.73
    зулта
    -0.67
     للاسماء
    -0.62
    addCriterion
    -0.62
     تانيه
    -0.61
    ViewFeatures
    -0.61
     éprou
    -0.60
    spender
    -0.59
    POSITIVE LOGITS
    Regards
    1.49
     Regards
    1.44
    Sincerely
    1.27
    regards
    1.23
     regards
    1.23
    Cheers
    1.17
    Yours
    1.04
     Cheers
    1.04
    Respectfully
    1.03
    Best
    1.03
    Activations Density 0.271%

    No Known Activations