© 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. 38-GEMMASCOPE-RES-16K
    11. 9726
    Prev
    Next
    INDEX
    Explanations

    the presence of decorative or artistic elements related to crafting

    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
     neighborhood
    -0.85
     flavorful
    -0.81
     honors
    -0.77
     colorful
    -0.77
    neighborhood
    -0.75
     și
    -0.74
    Neighborhood
    -0.74
     favorite
    -0.74
    Neighbors
    -0.74
     theater
    -0.73
    POSITIVE LOGITS
    Whilst
    2.14
     Whilst
    2.09
     whilst
    1.94
    initialise
    1.59
     maths
    1.52
     recognisable
    1.51
     localised
    1.51
     recognised
    1.48
     standardised
    1.48
     tyres
    1.47
    Activations Density 7.485%

    No Known Activations