© 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 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. 1235
    Prev
    Next
    INDEX
    Explanations

    the presence of the names "Jean" and "Jane."

    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
    RenderAtEndOf
    -1.02
     myſelf
    -1.01
     itſelf
    -1.01
     Monfieur
    -0.92
     nahilalakip
    -0.91
     Eſ
    -0.89
     يتيمه
    -0.89
     Efq
    -0.89
    曖昧さ回避
    -0.88
    AndEndTag
    -0.88
    POSITIVE LOGITS
     Jane
    1.87
     Jean
    1.65
    Jane
    1.64
    Jean
    1.43
    Jan
    1.42
     Jan
    1.39
    jan
    1.35
     JAN
    1.27
     JEAN
    1.27
     jane
    1.26
    Activations Density 0.051%

    No Known Activations