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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 11081
    Prev
    Next
    INDEX
    Explanations

    elements and their properties within a document, particularly in the context of programming or web development

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

    Code, filenames, or HTML

    np_acts-logits-general · gemini-2.0-flash

    code identifiers and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {},
    
    -0.59
    {})
    -0.58
    <>());
    -0.58
    ++;
    
    -0.52
    ()<<
    -0.52
     {}
    
    -0.52
     {};
    
    -0.51
    ({});
    -0.51
    )=>{
    
    -0.49
    Portály
    -0.48
    POSITIVE LOGITS
    IBarButtonItem
    0.72
    তথ্যসূত্র
    0.72
    DoubleQuotes
    0.72
     snippetHide
    0.69
    ChromeDriver
    0.67
     StringTokenizer
    0.66
    ViewImports
    0.63
    WriteBarrier
    0.63
    Референце
    0.63
     splits
    0.61
    Activations Density 0.112%

    No Known Activations