© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2257
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and terms related to corporate governance

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

    shareholders, boards, and corporate governance

    np_acts-logits-general · gemini-2.0-flash

    corporate governance and shareholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StateList
    -0.53
    interopRequire
    -0.51
    pulumi
    -0.50
    Salta
    -0.49
    expandindo
    -0.49
    жи
    -0.45
    Šaltiniai
    -0.45
    loroethane
    -0.45
    ]));
    -0.45
     الدولى
    -0.43
    POSITIVE LOGITS
     shareholder
    1.08
     shareholders
    0.95
     proxy
    0.93
     board
    0.91
     Board
    0.86
     Proxy
    0.85
    Board
    0.83
     stockholder
    0.83
     Shareholders
    0.80
     BOARD
    0.78
    Activations Density 0.238%

    No Known Activations