© 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. 41-GEMMASCOPE-RES-16K
    11. 6270
    Prev
    Next
    INDEX
    Explanations

    references to food-related themes and comfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •A bit unsettling behaviour
    Positive logits going wild there

    No Comments

    Negative Logits
     pò
    -0.39
    Grüsse
    -0.39
     jLabel
    -0.39
    〝
    -0.38
     initComponents
    -0.36
     affichés
    -0.36
     Lingkungan
    -0.36
    Autoritní
    -0.35
    ‘’
    -0.35
     
    -0.35
    POSITIVE LOGITS
    fucking
    0.81
     fucking
    0.80
     Fuck
    0.77
    FUCK
    0.76
     FUCKING
    0.76
    fuck
    0.76
    Fuck
    0.76
     fuck
    0.75
     Fucking
    0.75
     motherfucker
    0.73
    Activations Density 0.757%

    No Known Activations