© 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. 3577
    Prev
    Next
    INDEX
    Explanations

    technical terms and constructs related to programming and data manipulation

    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
     universes
    -0.48
    databases
    -0.46
     empires
    -0.44
     gouvernements
    -0.44
    actéristique
    -0.43
     symptom
    -0.43
    Databases
    -0.43
     Councils
    -0.41
     cocinas
    -0.41
     ingredient
    -0.41
    POSITIVE LOGITS
     items
    1.09
     elements
    0.98
     activities
    0.91
     goodies
    0.88
     antigens
    0.88
     ITEMS
    0.87
     aktiviteter
    0.87
     observables
    0.85
     actions
    0.85
    ThroughAttribute
    0.85
    Activations Density 1.950%

    No Known Activations