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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 15969
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothing and attire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.92
    migrationBuilder
    -0.81
    __':
    
    -0.81
    HomeAsUpEnabled
    -0.81
     propOrder
    -0.81
     <=",
    -0.77
    PreExecute
    -0.75
    crollView
    -0.74
     &___
    -0.72
     onPostExecute
    -0.70
    POSITIVE LOGITS
     wear
    1.14
    wear
    1.11
     Wear
    1.07
    Wear
    1.07
     wears
    1.06
     wearing
    1.03
     dress
    1.01
     wore
    1.00
     donned
    1.00
     Wearing
    0.99
    Activations Density 0.267%

    No Known Activations