© 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. 38-GEMMASCOPE-RES-16K
    11. 12793
    Prev
    Next
    INDEX
    Explanations

    references to desserts, specifically ice cream dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.60
     Infórmanos
    -0.59
     AssemblyTitle
    -0.58
     ويكيپيديا
    -0.55
    ControllerAdvice
    -0.51
    queryInterface
    -0.51
     AssemblyCompany
    -0.49
     ब्रेकडाउन
    -0.49
     canst
    -0.49
    StructEnd
    -0.49
    POSITIVE LOGITS
     ice
    0.80
     dessert
    0.78
     gelato
    0.72
     scoops
    0.71
     sorbet
    0.70
     scoop
    0.67
     vanilla
    0.66
     helado
    0.65
     Gel
    0.64
     моро
    0.62
    Activations Density 0.166%

    No Known Activations