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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6005
    Prev
    Next
    INDEX
    Explanations

    numbers and numeric expressions

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

    Sentences starting with "I," "We," "My," "For," or "Please."

    np_acts-logits-general · gemini-2.0-flash

    pronoun, number, or category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FontWeight
    -0.95
     RoutedEventArgs
    -0.95
    ChildScrollView
    -0.94
     MessageBoxIcon
    -0.93
     تضيفلها
    -0.88
     snippetHide
    -0.88
     يتيمه
    -0.88
    Datuak
    -0.88
    BorderFactory
    -0.86
    DockStyle
    -0.84
    POSITIVE LOGITS
    <eos>
    1.29
    ↵
    1.25
    ↵↵
    1.12
    ↵↵↵
    1.09
    ↵↵↵↵
    1.00
        
    0.98
    ↵↵↵↵↵
    0.97
            
    0.94
    <h2>
    0.90
    The
    0.90
    Activations Density 0.935%

    No Known Activations