© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7959
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.75
    epik
    -0.73
    tagext
    -0.70
    stasia
    -0.70
    APOLIS
    -0.68
    ELTS
    -0.68
    گي
    -0.68
     AppBundle
    -0.67
    jsonwebtoken
    -0.66
    الإنجليزية
    -0.66
    POSITIVE LOGITS
     there
    2.58
    there
    2.23
     THERE
    2.06
    There
    1.82
     There
    1.78
    THERE
    1.70
     allí
    1.25
     acolo
    1.19
    Theres
    1.18
     theres
    1.15
    Activations Density 0.110%

    No Known Activations