© 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
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 9834
    Prev
    Next
    INDEX
    Explanations

    information related to products and shipping details

    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
     totiž
    -0.56
     nämlich
    -0.52
     nemlig
    -0.51
     that
    -0.49
     here
    -0.48
     przecież
    -0.47
     so
    -0.47
     gobern
    -0.46
    怎樣
    -0.46
     thankfully
    -0.46
    POSITIVE LOGITS
     Includes
    1.23
     Requires
    1.11
    Includes
    1.09
    Requires
    0.96
     Contains
    0.94
    May
    0.88
     May
    0.88
     Must
    0.86
    Must
    0.84
    Contains
    0.82
    Activations Density 0.491%

    No Known Activations