© 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. 1-GEMMASCOPE-RES-16K
    6. 5640
    Prev
    Next
    INDEX
    Explanations

    scientific terminology and key concepts related to genetics and epidemiological studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wiesbaden
    -1.06
    ſelf
    -0.91
     Houſe
    -0.88
     Magdeburg
    -0.87
     Curitiba
    -0.86
     Mahomet
    -0.86
     itſelf
    -0.86
     Jokowi
    -0.85
     ſtate
    -0.85
     Majefty
    -0.84
    POSITIVE LOGITS
     Mos
    1.07
     Dor
    1.06
     Tar
    1.02
     Kar
    1.01
     Kam
    1.00
     Mil
    0.92
     Gil
    0.91
     Bay
    0.91
     Jam
    0.89
     Sak
    0.89
    Activations Density 2.820%

    No Known Activations