© 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. 3-GEMMASCOPE-RES-16K
    11. 2025
    Prev
    Next
    INDEX
    Explanations

    references to the concept of properness or appropriateness in contexts such as behavior, treatment, or etiquette

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SqlCommand
    -0.96
    onnaissance
    -0.95
    InjectAttribute
    -0.92
     ContentValues
    -0.89
     AssemblyVersion
    -0.88
     iCloud
    -0.88
    lofen
    -0.87
    appeal
    -0.86
    chenkt
    -0.86
     cune
    -0.85
    POSITIVE LOGITS
     proper
    3.01
     Proper
    2.96
    Proper
    2.86
    proper
    2.80
     PROPER
    2.70
     properly
    2.15
    properly
    2.01
     Properly
    2.01
     improper
    1.71
     Improper
    1.59
    Activations Density 0.044%

    No Known Activations