© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 705
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory processes, particularly in the context of documentation and formal procedures

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

    technical terms and parameters related to programming and layout design

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

    marburg, martinsburg, march, maroney, marty

    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
     Billy
    -0.50
    Billy
    -0.47
     ObjectId
    -0.47
    ObjectId
    -0.46
     cơ
    -0.45
    Executors
    -0.43
     thuê
    -0.43
    ObjectID
    -0.42
    nextDouble
    -0.41
     Heywood
    -0.40
    POSITIVE LOGITS
     MAR
    2.00
    MAR
    1.89
     mar
    1.88
    Mar
    1.72
    mar
    1.70
     Mar
    1.70
     Мар
    1.63
    mars
    1.58
     мар
    1.56
    Мар
    1.52
    Activations Density 0.063%

    No Known Activations