© 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. 11-GEMMASCOPE-RES-16K
    11. 12648
    Prev
    Next
    INDEX
    Explanations

    topics related to historical narratives and the representation of marginalized groups in history

    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
    CascadeType
    -0.56
    sizeCache
    -0.56
    참고
    -0.55
    PerformLayout
    -0.55
    XmlAccessType
    -0.54
     ELECTRONIC
    -0.53
    AddTagHelper
    -0.52
     StyleSheet
    -0.52
    IntoConstraints
    -0.52
     مرئيه
    -0.52
    POSITIVE LOGITS
     history
    0.76
     Geschichts
    0.75
     historians
    0.71
     History
    0.68
     historiador
    0.65
    History
    0.63
     HISTORY
    0.63
     histor
    0.61
    history
    0.60
     historia
    0.60
    Activations Density 0.591%

    No Known Activations