© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7498
    Prev
    Next
    INDEX
    Explanations

    phrases related to health, biological conditions, and patient outcomes

    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
    Liefs
    -0.36
     yanlış
    -0.36
    拙
    -0.35
    못
    -0.34
    こ
    -0.34
    borderFill
    -0.34
     schlecht
    -0.33
     хуже
    -0.33
     inevit
    -0.33
     gagal
    -0.33
    POSITIVE LOGITS
     intact
    1.80
     healthy
    1.74
     undamaged
    1.63
     unharmed
    1.55
    healthy
    1.45
    Healthy
    1.27
     functioning
    1.20
     Healthy
    1.20
     healthier
    1.19
     unaffected
    1.19
    Activations Density 1.030%

    No Known Activations