© 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. 37-GEMMASCOPE-RES-16K
    11. 7867
    Prev
    Next
    INDEX
    Explanations

    expressions related to being busy or overwhelmed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accesso
    -0.32
     mahdol
    -0.32
     duración
    -0.31
    Durée
    -0.28
     duração
    -0.28
     اختی
    -0.28
    grenze
    -0.27
    XmlRootElement
    -0.27
    beelding
    -0.26
    anjutnya
    -0.26
    POSITIVE LOGITS
     busy
    3.23
    busy
    2.81
     Busy
    2.72
    Busy
    2.64
     busiest
    2.27
    忙
    2.23
     sibuk
    2.20
    忙しい
    2.00
    BUSY
    1.98
     hectic
    1.91
    Activations Density 0.329%

    No Known Activations