© 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. 528
    Prev
    Next
    INDEX
    Explanations

    references to legislation and government actions

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

    9/11 and World Trade Center

    np_acts-logits-general · gemini-2.0-flash

    9/11 attacks

    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
    DoubleQuotes
    -0.83
    ⓧ
    -0.82
     Chwiliwch
    -0.74
     nahilalakip
    -0.73
     дописавши
    -0.73
    Autoritní
    -0.68
    sizeCache
    -0.68
     AttributeSet
    -0.67
    HasBeenSet
    -0.67
    ècie
    -0.67
    POSITIVE LOGITS
     September
    0.90
     Sept
    0.87
     terrorist
    0.83
     terrorists
    0.77
     attacks
    0.75
     Terror
    0.75
    September
    0.73
     terrorism
    0.73
     attaques
    0.70
    Terror
    0.67
    Activations Density 0.111%

    No Known Activations