© 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. 9583
    Prev
    Next
    INDEX
    Explanations

    narrative elements involving intimate actions and physical interactions

    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
     Italijanski
    -0.57
     Италијани
    -0.54
    webElementXpaths
    -0.53
     informée
    -0.50
     незавершена
    -0.50
     चीज़ों
    -0.47
     transfieras
    -0.46
    ंदीखरीदारी
    -0.45
     Roskov
    -0.44
    ÁL
    -0.44
    POSITIVE LOGITS
    +#+#
    0.37
     habido
    0.36
     HasFactory
    0.36
    CloseOperation
    0.35
     conmigo
    0.35
    #
    0.34
    RuleContext
    0.33
    BufferException
    0.32
     otomatig
    0.32
     Zwiebel
    0.32
    Activations Density 0.336%

    No Known Activations