© 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. 39-GEMMASCOPE-RES-16K
    11. 2340
    Prev
    Next
    INDEX
    Explanations

    medical conditions and patient demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oprot
    -0.36
     ajudá
    -0.34
     facilitated
    -0.32
     geführt
    -0.32
     enabled
    -0.30
     Italijanski
    -0.28
    liceerd
    -0.28
     invi
    -0.28
     ayudado
    -0.28
     guided
    -0.28
    POSITIVE LOGITS
     suffer
    1.33
     suffers
    1.27
     suffered
    1.22
     developed
    1.20
     develops
    1.19
     develop
    1.16
    developed
    1.14
     développ
    1.10
     suffering
    1.09
    develop
    1.07
    Activations Density 0.602%

    No Known Activations