© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4826
    Prev
    Next
    INDEX
    Explanations

    concepts related to respect and civility in social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.36
     phú
    -0.36
    SpringRunner
    -0.33
     Diagnos
    -0.32
    Życiorys
    -0.30
     financieras
    -0.30
     Anhang
    -0.30
    Биография
    -0.30
     DIAG
    -0.29
     трево
    -0.29
    POSITIVE LOGITS
     etiquette
    1.57
     manners
    1.52
     politeness
    1.50
     courtesy
    1.49
     polite
    1.46
     courteous
    1.41
     civility
    1.40
    courtesy
    1.31
     Etiquette
    1.28
     Courtesy
    1.23
    Activations Density 0.441%

    No Known Activations