© 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. 33-GEMMASCOPE-RES-16K
    11. 9140
    Prev
    Next
    INDEX
    Explanations

    phrases related to author contributions and data availability in research articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ODE
    -0.31
    conto
    -0.29
    viti
    -0.29
    agam
    -0.28
    dotenv
    -0.28
    angos
    -0.28
    stdlib
    -0.28
    Eksteraj
    -0.28
     keres
    -0.28
     iti
    -0.27
    POSITIVE LOGITS
     author
    3.28
     authors
    3.03
    author
    2.61
     Author
    2.56
    authors
    2.48
     Authors
    2.47
    Author
    2.42
    作者
    2.41
     AUTHOR
    2.27
    Authors
    2.20
    Activations Density 0.973%

    No Known Activations