Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16012
    Prev
    Next
    INDEX
    Explanations

    references to financial obligations or tax-related issues concerning public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Celebrities, fashion, and runway events

    np_acts-logits-general · gemini-2.0-flash

    fashion and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.70
    RegressionTest
    -0.57
    RectangleBorder
    -0.56
    addCriterion
    -0.55
     fieldNum
    -0.54
    وصلات
    -0.54
    ValueGenerated
    -0.54
     <=",
    -0.54
    BASEPATH
    -0.54
    \{\\
    -0.54
    POSITIVE LOGITS
     fashion
    1.23
     Fashion
    1.08
    fashion
    1.07
    Fashion
    0.97
     Vogue
    0.96
     runway
    0.91
     FASHION
    0.91
     catwalk
    0.86
    Vogue
    0.84
     couture
    0.77
    Activations Density 0.075%

    No Known Activations