© 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. 11-GEMMASCOPE-RES-16K
    11. 10655
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate quality, particularly the term "well" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schaefer
    -0.85
     Nugent
    -0.79
    ობ
    -0.77
    jstor
    -0.75
    ᾶ
    -0.73
     whoſe
    -0.73
     onItemClick
    -0.73
    TableBody
    -0.70
     invocation
    -0.69
    Programming
    -0.69
    POSITIVE LOGITS
     well
    1.37
     WELL
    1.36
     Well
    1.29
    well
    1.26
     Wells
    1.26
    Well
    1.23
    Wells
    1.20
     wells
    1.18
     Welles
    1.12
     WELLS
    1.10
    Activations Density 0.089%

    No Known Activations