© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 10411
    Prev
    Next
    INDEX
    Explanations

    mentions of algorithms and their implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.46
     cómodo
    -0.45
    FromNib
    -0.43
    ፩
    -0.42
     Américas
    -0.41
     ancla
    -0.41
     comunión
    -0.41
     administrativos
    -0.41
     jambe
    -0.41
     cómoda
    -0.41
    POSITIVE LOGITS
     AI
    2.33
    AI
    1.99
     Artificial
    1.96
     artificial
    1.95
    Artificial
    1.77
    artificial
    1.56
    人工智能
    1.48
     ai
    1.48
     künst
    1.41
     искус
    1.40
    Activations Density 0.371%

    No Known Activations