© 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. 3-GEMMASCOPE-RES-16K
    11. 1072
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Joseph."

    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
     Galla
    -0.70
    __(/*!
    -0.65
     Tand
    -0.64
    czer
    -0.63
    Lugares
    -0.63
     Deel
    -0.61
     Galer
    -0.61
    ierno
    -0.60
     Yamada
    -0.60
     Darío
    -0.59
    POSITIVE LOGITS
     Joseph
    2.25
    Joseph
    2.12
     joseph
    1.85
     JOSEPH
    1.84
    joseph
    1.74
    JOSEPH
    1.63
     Egypt
    1.32
    Egypt
    1.30
     EGYPT
    1.06
     Egyptian
    1.03
    Activations Density 0.065%

    No Known Activations