© 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 EvalsExportsinterp-engineNEWAPI 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. 1567
    Prev
    Next
    INDEX
    Explanations

    terms related to legal decisions and judgments

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

    "in favor"

    np_acts-logits-general · gemini-2.0-flash

    in favor of

    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
    ⓧ
    -0.60
    tagext
    -0.54
     Ause
    -0.53
     gevo
    -0.50
    ubility
    -0.48
    المكان
    -0.47
    الدراسه
    -0.47
    InvalidProtocol
    -0.47
    těte
    -0.47
    kommen
    -0.47
    POSITIVE LOGITS
     favor
    2.61
     favour
    2.31
    favor
    1.97
     FAVOR
    1.89
     faveur
    1.83
     Favor
    1.78
     favors
    1.69
     favore
    1.64
    fav
    1.63
    Favor
    1.54
    Activations Density 0.288%

    No Known Activations