© 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. 9400
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical treatments and immunology

    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
     Bany
    -0.83
     Blackburn
    -0.78
     autorytatywna
    -0.73
     Mejía
    -0.71
    ussis
    -0.71
    ipzig
    -0.70
     Wein
    -0.68
     Jop
    -0.64
    ValueStyle
    -0.64
     comor
    -0.63
    POSITIVE LOGITS
    Lähteet
    0.88
     Basu
    0.84
     Budd
    0.82
     EVAL
    0.81
     Ponte
    0.79
     niggas
    0.79
     Gaut
    0.78
     Sculpture
    0.78
     Cess
    0.78
     Cheyenne
    0.77
    Activations Density 1.868%

    No Known Activations