© 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. 10-GEMMASCOPE-RES-16K
    11. 10408
    Prev
    Next
    INDEX
    Explanations

    references to medical or scientific terminology, particularly in relation to metabolic processes and specific research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -1.18
    hasMoreElements
    -0.95
     виправивши
    -0.89
    )")
    -0.88
    fucker
    -0.87
    TypeDef
    -0.86
    ...")
    -0.85
    iyor
    -0.85
    !")
    -0.84
     Perſ
    -0.82
    POSITIVE LOGITS
     Fawcett
    0.78
     GX
    0.76
    Hau
    0.69
    derry
    0.67
     Faw
    0.65
     Stowe
    0.64
     McDermott
    0.64
    GX
    0.64
    ndice
    0.64
     McLaughlin
    0.64
    Activations Density 1.563%

    No Known Activations