© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7383
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only" and its variations, highlighting exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    ViewFeatures
    -0.77
     Verdi
    -0.69
     Calhoun
    -0.68
     Schubert
    -0.66
     hereof
    -0.66
    $($
    -0.66
    Korn
    -0.65
     mellitus
    -0.65
     condom
    -0.65
     Davenport
    -0.64
    POSITIVE LOGITS
     only
    1.36
     Only
    1.18
     ONLY
    1.14
    ONLY
    1.13
    Sólo
    1.08
    Only
    1.07
    nly
    1.01
    only
    0.99
     sólo
    0.92
     лишь
    0.91
    Activations Density 0.143%

    No Known Activations