© 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. 10-GEMMASCOPE-RES-16K
    11. 10458
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to societal expectations and moral questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сылкі
    -0.38
    reportWebVitals
    -0.38
     estan
    -0.38
     tartalomajánló
    -0.36
     שוליים
    -0.35
     tillbaka
    -0.35
     tertentu
    -0.33
     cierta
    -0.33
     bParam
    -0.33
     prostřed
    -0.31
    POSITIVE LOGITS
    ValueStyle
    0.52
     désolés
    0.48
    こんな
    0.47
    thâu
    0.47
     Thi
    0.46
    しかも
    0.45
    あんな
    0.45
     こんな
    0.45
    这样一个
    0.44
    kyu
    0.44
    Activations Density 0.909%

    No Known Activations