© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1455
    Prev
    Next
    INDEX
    Explanations

    terms associated with biological processes and medical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.76
    versiti
    -0.69
    gridx
    -0.68
    بوابة
    -0.64
    entiary
    -0.64
    OrWhiteSpace
    -0.64
     Keys
    -0.63
     Wheatley
    -0.62
    piratory
    -0.61
     LIMITS
    -0.61
    POSITIVE LOGITS
     Jefus
    0.96
     Anſ
    0.91
     ſtate
    0.91
     purpoſe
    0.88
     poffe
    0.84
     itſelf
    0.82
     Majefty
    0.81
     fufficient
    0.80
     Houſe
    0.80
     Nuremberg
    0.80
    Activations Density 1.835%

    No Known Activations