© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    elements related to political elections and competition outcomes

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

    Prepositions indicating spatial relations

    np_acts-logits-general · gemini-2.0-flash

    ahead or beating

    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
    NUMX
    -0.64
    setVerticalGroup
    -0.60
     Màu
    -0.56
    ursor
    -0.55
    âteau
    -0.55
    "';
    -0.53
    ==="
    -0.53
    plevel
    -0.53
    intur
    -0.52
    makeConstraints
    -0.52
    POSITIVE LOGITS
     ahead
    1.29
     beating
    1.04
    ahead
    1.00
     beat
    0.99
     narrowly
    0.90
     davanti
    0.89
     beaten
    0.89
     devant
    0.88
     AHEAD
    0.87
     Ahead
    0.86
    Activations Density 0.159%

    No Known Activations