© 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. 2-GEMMASCOPE-RES-16K
    11. 4971
    Prev
    Next
    INDEX
    Explanations

    instances of the word "design" and its variations, indicating a focus on design-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Designing
    -0.57
    Designing
    -0.57
     designing
    -0.56
     Einfluß
    -0.48
     diseñados
    -0.47
    Autoritní
    -0.46
     posesión
    -0.43
     deberes
    -0.43
    Designer
    -0.43
    お手
    -0.40
    POSITIVE LOGITS
     design
    0.84
     accepted
    0.60
     accept
    0.59
     vendor
    0.56
    accepted
    0.54
     Markets
    0.54
     contextLoads
    0.53
     Accepted
    0.51
     дизайн
    0.48
     simplifié
    0.47
    Activations Density 0.112%

    No Known Activations