© 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. 36-GEMMASCOPE-RES-16K
    11. 9453
    Prev
    Next
    INDEX
    Explanations

    words related to actions and events in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ErrIntOverflow
    -0.47
    AnimationsModule
    -0.38
     procedere
    -0.36
    ChildScrollView
    -0.36
     handling
    -0.35
     progress
    -0.34
     postup
    -0.33
     dealt
    -0.33
     konzent
    -0.33
     dealing
    -0.33
    POSITIVE LOGITS
     rename
    0.73
     tattooed
    0.71
     EconPapers
    0.71
     tattoo
    0.70
     nicknamed
    0.68
     boycot
    0.68
     famously
    0.68
     renaming
    0.66
     tattoos
    0.65
     accidentally
    0.65
    Activations Density 0.828%

    No Known Activations