© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 51318
    Prev
    Next
    INDEX
    Explanations

    references to high-stakes situations or the concept of stakes involved in decisions

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

    high-stakes world or importance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    حياته
    -0.75
     للمعارف
    -0.74
     otomatig
    -0.67
     Transports
    -0.67
     endregion
    -0.66
    initializeApp
    -0.65
     ویکی‌پدی
    -0.65
     CMV
    -0.64
     transports
    -0.63
    حياتها
    -0.63
    POSITIVE LOGITS
    Stake
    0.97
     Stake
    0.94
     stake
    0.90
    stake
    0.83
     stakes
    0.66
     Stakes
    0.63
    Staking
    0.57
     enjeux
    0.56
    stakes
    0.55
     staked
    0.53
    Activations Density 0.004%

    No Known Activations