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. 8192
    Prev
    Next
    INDEX
    Explanations

    references to cancer treatment mechanisms and biological processes

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

    Following "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    specific or particular

    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
    IContainer
    -0.79
     initComponents
    -0.75
    __':
    
    -0.66
    WithMany
    -0.59
     betweenstory
    -0.58
     transférez
    -0.55
    ViewImports
    -0.54
    __":
    
    -0.54
     crossorigin
    -0.53
    Билгалдахарш
    -0.52
    POSITIVE LOGITS
     special
    2.90
     specific
    2.89
     specifically
    2.70
    specific
    2.65
    special
    2.63
     Specific
    2.62
    Specific
    2.61
     SPECIFIC
    2.50
     khusus
    2.47
     específico
    2.45
    Activations Density 0.815%

    No Known Activations