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

    Neuronpedia

    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. 10588
    Prev
    Next
    INDEX
    Explanations

    molecules related to kinase activity and their roles in signaling pathways

    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
     estekak
    -0.55
     aren
    -0.54
    Couldn
    -0.48
     MEANS
    -0.47
    Sounds
    -0.47
     Sounds
    -0.46
     weren
    -0.46
     nakalista
    -0.45
     Means
    -0.45
    Geplaatst
    -0.45
    POSITIVE LOGITS
     exhibits
    0.93
     forms
    0.74
     causes
    0.71
     experiences
    0.69
     results
    0.68
     possesses
    0.66
     displays
    0.66
     acts
    0.65
     mod
    0.65
     controls
    0.64
    Activations Density 1.670%

    No Known Activations