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. 24-GEMMASCOPE-RES-16K
    6. 8204
    Prev
    Next
    INDEX
    Explanations

    references to fabric and sewing supplies

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

    relating to shops or purchasing goods

    np_acts-logits-general · gemini-2.0-flash

    stores and shops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.76
    tvguidetime
    -0.59
     ospiti
    -0.59
     Italijanski
    -0.58
     breweries
    -0.56
    ivamente
    -0.55
    ArrowToggle
    -0.54
    afficheront
    -0.54
    protoimpl
    -0.53
     محفوظة
    -0.53
    POSITIVE LOGITS
     store
    1.25
     stores
    1.15
     Store
    0.94
     Stores
    0.92
     shops
    0.92
    store
    0.91
     shop
    0.90
     retailer
    0.89
     STORE
    0.86
     retail
    0.84
    Activations Density 0.189%

    No Known Activations