© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 5943
    Prev
    Next
    INDEX
    Explanations

    elements related to etiquette and manners in social interactions

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

    polite social interactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.70
     Grüsse
    -0.60
    EndGlobalSection
    -0.57
    RegressionTest
    -0.52
     Roskov
    -0.51
    uyasha
    -0.49
    Vidite
    -0.49
    (!__
    -0.49
    .*")]
    -0.49
    $_['
    -0.47
    POSITIVE LOGITS
     aimable
    0.41
     Stoll
    0.38
     elegant
    0.38
     ràng
    0.38
     politely
    0.37
     Char
    0.37
     Cigar
    0.37
     courteous
    0.37
     char
    0.36
     elegantly
    0.36
    Activations Density 0.180%

    No Known Activations