© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8298
    Prev
    Next
    INDEX
    Explanations

    terms related to romantic themes and celebrations

    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
    UserScript
    -0.71
     kasarigan
    -0.66
     AssemblyCulture
    -0.61
    WriteTagHelper
    -0.59
    Sucesor
    -0.58
     dAtA
    -0.56
    <unused79>
    -0.55
     stiefe
    -0.55
    <unused52>
    -0.55
    <unused21>
    -0.55
    POSITIVE LOGITS
     romantic
    0.72
     romantique
    0.63
     romantis
    0.62
    Romantic
    0.61
     Romantic
    0.58
     honeymoon
    0.53
     عاشقانه
    0.52
     amoureux
    0.51
    romantic
    0.50
     роман
    0.50
    Activations Density 0.227%

    No Known Activations