© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10506
    Prev
    Next
    INDEX
    Explanations

    structured data related to organizational roles and responsibilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    currently
    -0.59
     maintenant
    -0.59
     currently
    -0.58
     teď
    -0.57
     sekarang
    -0.57
     attualmente
    -0.57
     ahora
    -0.56
     nyní
    -0.56
     now
    -0.55
     actuellement
    -0.55
    POSITIVE LOGITS
     was
    0.79
     volna
    0.64
     originally
    0.56
    もありました
    0.56
     wasn
    0.55
     knew
    0.55
    当时
    0.55
     damaligen
    0.53
     meant
    0.52
     podía
    0.52
    Activations Density 2.252%

    No Known Activations