© 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. 35-GEMMASCOPE-RES-16K
    11. 9944
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and reflections related to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为例
    -0.33
     jaké
    -0.29
    `${
    -0.28
    archiviato
    -0.27
    Биография
    -0.25
    selaer
    -0.24
    どんな
    -0.24
    Ārējās
    -0.24
    <tbody>
    -0.23
    tersebut
    -0.23
    POSITIVE LOGITS
     something
    4.28
    something
    3.72
    Something
    3.64
     Something
    3.59
     SOMETHING
    3.00
     qualcosa
    2.97
     sesuatu
    2.70
     somethin
    2.67
     iets
    2.56
     coś
    2.50
    Activations Density 1.100%

    No Known Activations