© 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. 10-GEMMASCOPE-RES-16K
    11. 3062
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "work" and its context within different sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capuz
    -0.56
     cadeia
    -0.54
     pingente
    -0.54
    sidemargin
    -0.54
     coroa
    -0.54
    istoitu
    -0.54
    rrggbb
    -0.52
    Sagittarius
    -0.51
     mídia
    -0.50
    iddhar
    -0.50
    POSITIVE LOGITS
    Work
    1.37
    Working
    1.30
     working
    1.29
     Work
    1.28
    working
    1.27
     work
    1.26
    work
    1.22
     Working
    1.21
     WORK
    1.16
    WORKING
    1.12
    Activations Density 0.164%

    No Known Activations