© 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-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 12067
    Prev
    Next
    INDEX
    Explanations

    legal terminology and phrases related to exceptions in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.56
    rrggbb
    -0.56
    Hozzáférés
    -0.55
    endregion
    -0.49
    ArgumentParser
    -0.47
     różne
    -0.45
    sizeCache
    -0.45
    Бахар
    -0.45
    CodeAttribute
    -0.43
    innerWidth
    -0.43
    POSITIVE LOGITS
     rare
    2.17
     few
    1.81
    rare
    1.80
     rares
    1.73
    Rare
    1.71
     rarer
    1.70
     infrequent
    1.70
     rarest
    1.66
     Rare
    1.65
     RARE
    1.65
    Activations Density 1.051%

    No Known Activations