© 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. 11-GEMMASCOPE-RES-16K
    11. 10949
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude, support, and loyalty

    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
     lhes
    -0.39
    ierungs
    -0.38
    новништво
    -0.38
    لينكات
    -0.37
    remark
    -0.37
    makanan
    -0.36
    paign
    -0.36
     lele
    -0.36
    本文
    -0.35
     Disadvantages
    -0.35
    POSITIVE LOGITS
    IsMutable
    0.54
    BufferException
    0.54
     Италијани
    0.54
    httphttps
    0.53
     AspNetCore
    0.53
    oredCriteria
    0.52
    StoryboardSegue
    0.49
    windowFixed
    0.47
     respaldo
    0.46
    يكب
    0.45
    Activations Density 0.267%

    No Known Activations