© 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. 9518
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or technical conditions and scenarios involving stimuli and responses

    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
    IT
    -0.77
    IC
    -0.67
     IT
    -0.61
     IC
    -0.60
    it
    -0.60
    IL
    -0.60
    IK
    -0.59
     IE
    -0.59
    IS
    -0.59
    IE
    -0.59
    POSITIVE LOGITS
    :✨
    0.70
    utilisons
    0.48
    DIPSETTING
    0.44
     StatefulWidget
    0.44
    iodía
    0.42
     indisponible
    0.42
    Referencies
    0.38
     kasarigan
    0.38
    ValueStyle
    0.37
    homonymie
    0.36
    Activations Density 0.489%

    No Known Activations