© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 1
    Prev
    Next
    INDEX
    Explanations

    the word "qui" indicating questions or clauses where the subject is being referenced, and it also highlights the concept of maintenance in contexts related to service or care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁴
    -0.60
     pleaſure
    -0.49
    scrapy
    -0.47
     masterpiece
    -0.46
     eel
    -0.46
    fromnode
    -0.46
    Hentet
    -0.46
    Meteor
    -0.46
     practica
    -0.45
     comod
    -0.45
    POSITIVE LOGITS
    submit
    0.70
    submissions
    0.58
     Submit
    0.56
    assert
    0.54
    Submissions
    0.52
    maintain
    0.51
     maintain
    0.50
    maintained
    0.50
    SUBMIT
    0.50
     submissions
    0.50
    Activations Density 0.154%

    No Known Activations