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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1111
    Prev
    Next
    INDEX
    Explanations

    legislative and electoral terminology

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

    terms related to political constituencies and electoral processes

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

    numbering rules and calendar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.68
    Personensuche
    -0.67
    OGND
    -0.59
    帖最后由
    -0.57
     оригіналу
    -0.57
    InstanceState
    -0.55
    日閲覧
    -0.54
     ddelweddau
    -0.54
    moine
    -0.54
    queryInterface
    -0.54
    POSITIVE LOGITS
     system
    2.08
    system
    1.79
     System
    1.74
     système
    1.66
     sistema
    1.65
     SYSTEM
    1.62
    System
    1.61
     systems
    1.59
     syste
    1.56
     systeem
    1.56
    Activations Density 0.302%

    No Known Activations