© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 11817
    Prev
    Next
    INDEX
    Explanations

    medical terms related to adverse effects and safety information in drug usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaços
    -0.44
     disambiguazione
    -0.43
    SpringRunner
    -0.43
    WebServlet
    -0.43
     Arri
    -0.40
     dima
    -0.39
    DockStyle
    -0.39
     defen
    -0.39
    GenerationType
    -0.38
    ClientRect
    -0.37
    POSITIVE LOGITS
     side
    1.38
     adverse
    1.24
     Side
    1.18
    Side
    1.13
    Adverse
    1.11
     SIDE
    1.10
     Nebenwirkungen
    1.07
     Adverse
    1.05
    副作用
    1.04
     reactions
    1.00
    Activations Density 1.369%

    No Known Activations