© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14115
    Prev
    Next
    INDEX
    Explanations

    topics related to the fashion and garment industry, particularly focusing on trends, sewing, and societal impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inerja
    -0.59
     actes
    -0.51
     مشين
    -0.50
    ękuję
    -0.50
     içi
    -0.49
    leich
    -0.48
    getSupport
    -0.48
    PostExecute
    -0.48
     спектак
    -0.47
    🏾
    -0.47
    POSITIVE LOGITS
     trend
    2.25
     trends
    2.05
    trend
    1.94
     Trend
    1.92
    Trend
    1.90
     trending
    1.86
     Trends
    1.75
     trendy
    1.73
    trends
    1.71
    Trends
    1.67
    Activations Density 0.209%

    No Known Activations