© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2528
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or actions

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

    Begins with "who" and contains a verb

    np_acts-logits-general · gemini-2.0-flash

    who performed action

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     الحره
    -0.80
    
    -0.78
    AccessorTable
    -0.74
    出版年
    -0.66
     odkazy
    -0.62
     betweenstory
    -0.61
    COUVER
    -0.60
    setVerticalGroup
    -0.60
    enumii
    -0.58
     onBind
    -0.57
    POSITIVE LOGITS
     responsible
    0.88
     authored
    0.86
     instig
    0.82
     initiated
    0.78
     Responsible
    0.75
     initiating
    0.75
    responsible
    0.74
     owns
    0.72
    Responsible
    0.70
     created
    0.70
    Activations Density 0.501%

    No Known Activations