© 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. 11-GEMMASCOPE-RES-16K
    11. 8206
    Prev
    Next
    INDEX
    Explanations

    references to laboratories and related scientific or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     baloncesto
    -0.52
    sze
    -0.48
     touristique
    -0.48
    씀
    -0.47
     présidentielle
    -0.46
     yym
    -0.45
     tourisme
    -0.45
    arthritis
    -0.45
     Penyakit
    -0.45
     desmotiv
    -0.45
    POSITIVE LOGITS
     laboratory
    1.68
     lab
    1.59
     Laboratory
    1.52
    laboratory
    1.46
     Lab
    1.45
    Laboratory
    1.45
    Lab
    1.40
    lab
    1.37
     laboratorio
    1.37
     LAB
    1.36
    Activations Density 0.142%

    No Known Activations