© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 7963
    Prev
    Next
    INDEX
    Explanations

    phrases and guidelines related to social etiquette and behavior in dining situations

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

    associated with tips or recommendations

    np_acts-logits-general · gemini-2.0-flash

    advice and tips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.78
    новништво
    -0.76
     initComponents
    -0.72
     betweenstory
    -0.70
     ostavi
    -0.69
    fromnode
    -0.68
    PerformLayout
    -0.66
    󠁴
    -0.63
    twimg
    -0.62
     Drapeau
    -0.60
    POSITIVE LOGITS
     rule
    0.61
     tips
    0.60
     best
    0.60
     tip
    0.57
     Tips
    0.56
     consiglio
    0.56
    Tips
    0.55
     recommended
    0.55
     can
    0.55
    ilarang
    0.54
    Activations Density 0.230%

    No Known Activations