© 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. 15-GEMMASCOPE-RES-16K
    11. 5738
    Prev
    Next
    INDEX
    Explanations

    terms related to various medical and biological concepts, specifically focusing on conditions, measurements, and common treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haca
    -0.59
     pama
    -0.59
     purpoſe
    -0.58
     reaſon
    -0.58
     HasFactory
    -0.56
     myſelf
    -0.56
     leaſt
    -0.55
     themſelves
    -0.55
    uarts
    -0.55
     незавершена
    -0.55
    POSITIVE LOGITS
     lost
    0.59
    عدم
    0.58
     loss
    0.57
     failure
    0.54
     changes
    0.53
     change
    0.53
    acional
    0.52
     mismatch
    0.51
     imbalance
    0.51
     mis
    0.48
    Activations Density 0.742%

    No Known Activations