© 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. 19-GEMMASCOPE-RES-16K
    11. 10600
    Prev
    Next
    INDEX
    Explanations

    references to scientific examinations of cells and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oignons
    -0.52
     Bestimm
    -0.50
     szüks
    -0.43
     chegada
    -0.43
     Económica
    -0.42
     samband
    -0.42
    ثم
    -0.41
     hänen
    -0.40
     prossimo
    -0.40
     quedado
    -0.40
    POSITIVE LOGITS
     studied
    1.77
     examined
    1.66
     investigated
    1.65
     tested
    1.51
     analyzed
    1.44
     surveyed
    1.44
     analysed
    1.40
    studied
    1.39
     reviewed
    1.36
     Studied
    1.28
    Activations Density 0.926%

    No Known Activations