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. 20-GEMMASCOPE-RES-16K
    6. 13791
    Prev
    Next
    INDEX
    Explanations

    symbols and terms related to programming or coding concepts

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

    Code snippets and image-related tokens

    np_acts-logits-general · gemini-2.0-flash

    lists identifiers in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -1.77
     AssemblyCulture
    -1.60
    aarrggbb
    -1.59
    featureID
    -1.50
    脚注の使い方
    -1.44
     ExecuteAsync
    -1.43
     '\\;'
    -1.43
     defaultstate
    -1.40
    sizeCache
    -1.39
    ArrowToggle
    -1.38
    POSITIVE LOGITS
    </strong>
    0.59
    ↵↵↵
    0.58
     de
    0.54
    <strong>
    0.52
     
    0.51
      
    0.49
    <eos>
    0.48
    <unused63>
    0.46
    <h1>
    0.45
        
    0.45
    Activations Density 0.859%

    No Known Activations