© 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. 4-GEMMASCOPE-RES-16K
    11. 13261
    Prev
    Next
    INDEX
    Explanations

    mentions of familial or generational titles, particularly "Jr." and "Sr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marken
    -0.63
    ellation
    -0.63
     poli
    -0.62
     Anis
    -0.62
    Berger
    -0.61
    Erich
    -0.61
    条
    -0.60
     Barlow
    -0.60
     enc
    -0.60
     chain
    -0.59
    POSITIVE LOGITS
     Jr
    2.31
     Junior
    1.99
     junior
    1.94
    junior
    1.91
    Junior
    1.88
     jr
    1.84
     JUNIOR
    1.79
    Jr
    1.79
     juniors
    1.57
     Júnior
    1.50
    Activations Density 0.068%

    No Known Activations