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. 18-GEMMASCOPE-RES-16K
    6. 3139
    Prev
    Next
    INDEX
    Explanations

    discussions on economic incentives and public policy issues, particularly related to health care and taxation

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

    "incentive" or "encourage" related words

    np_acts-logits-general · gemini-2.0-flash

    incentive, rewards, and encouragement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.81
    Vidite
    -0.65
     communs
    -0.62
    (!__
    -0.60
     nahilalakip
    -0.60
     ProtoMessage
    -0.60
     referenties
    -0.59
    Билгалдахарш
    -0.55
    ьаж
    -0.55
    ʒ
    -0.54
    POSITIVE LOGITS
     incentive
    1.78
     incentiv
    1.68
     incentives
    1.62
    Incenti
    1.58
    incenti
    1.57
     incenti
    1.53
     Incentive
    1.42
     encourage
    1.39
     Incentives
    1.39
     Incenti
    1.35
    Activations Density 0.419%

    No Known Activations