© 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. 12281
    Prev
    Next
    INDEX
    Explanations

    mentions of retirement or transitions in career

    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
     acessar
    -0.58
    labeled
    -0.58
     dezelve
    -0.58
     ubica
    -0.56
     labeled
    -0.56
    Upcoming
    -0.54
     critters
    -0.54
     modeled
    -0.53
     behaviors
    -0.52
     așa
    -0.52
    POSITIVE LOGITS
     connexion
    0.60
     connexions
    0.51
     enquiries
    0.49
    :—
    0.48
     shewn
    0.48
     ialah
    0.47
     specialised
    0.47
     petrol
    0.46
     organisation
    0.45
    Colour
    0.44
    Activations Density 0.351%

    No Known Activations