Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12807
    Prev
    Next
    INDEX
    Explanations

    references to rules and regulations related to occupational safety and health

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

    preceding "rule", "report", "action", or "cases"

    np_acts-logits-general · gemini-2.0-flash

    rules and regulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.81
     незавершена
    -0.80
    printStackTrace
    -0.79
    +#+
    -0.71
    AutoresizingMask
    -0.62
    الإنجليزية
    -0.62
    UIControlState
    -0.62
    CloseOperation
    -0.61
     doInBackground
    -0.61
    lencia
    -0.58
    POSITIVE LOGITS
     rule
    0.91
     propOrder
    0.84
     proposed
    0.81
    rule
    0.80
    proposed
    0.73
     finalised
    0.72
     Proposed
    0.71
     published
    0.70
     Rule
    0.68
     RULE
    0.68
    Activations Density 0.590%

    No Known Activations