© 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. 37-GEMMASCOPE-RES-16K
    11. 6662
    Prev
    Next
    INDEX
    Explanations

    references to literary or artistic works and their elements

    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
     Manuals
    -0.60
     documentaries
    -0.58
     manuals
    -0.58
     Novels
    -0.56
    ParallelGroup
    -0.56
     boeken
    -0.53
    Books
    -0.50
     magazines
    -0.50
     audiobooks
    -0.50
     catalogues
    -0.50
    POSITIVE LOGITS
     piece
    1.20
     poem
    1.15
     article
    1.04
     document
    0.89
    piece
    0.85
     masterpiece
    0.83
     manuscript
    0.81
     report
    0.80
    poem
    0.79
     story
    0.79
    Activations Density 1.336%

    No Known Activations