© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14483
    Prev
    Next
    INDEX
    Explanations

    various forms and contexts of the word "policy."

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

    after "policy"

    np_acts-logits-general · gemini-2.0-flash

    policy making

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    تقاوى
    -0.66
     تضيفلها
    -0.61
    WebVitals
    -0.60
    __':
    
    -0.59
    gister
    -0.57
    TintMode
    -0.56
    BarStyle
    -0.56
    Демографія
    -0.56
     FetchType
    -0.54
     cherchés
    -0.54
    POSITIVE LOGITS
    maker
    0.96
     policies
    0.90
     makers
    0.87
    Policies
    0.83
    makers
    0.79
    making
    0.79
     Policies
    0.77
    holder
    0.72
    holders
    0.70
    policies
    0.67
    Activations Density 0.052%

    No Known Activations