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. 2336
    Prev
    Next
    INDEX
    Explanations

    beginning of a document or section

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

    Text fragments starting mid-sentence

    np_acts-logits-general · gemini-2.0-flash

    opening quotes and symbols

    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
    __":
    
    -0.85
    ↵↵
    -0.80
     utafitiHapana
    -0.77
    webElementXpaths
    -0.77
    aarrggbb
    -0.77
     snippetHide
    -0.74
    ----</
    -0.73
     المعيارى
    -0.73
    AndEndTag
    -0.72
    transQ
    -0.68
    POSITIVE LOGITS
    “
    0.65
    is
    0.61
    (
    0.60
          
    0.56
     époux
    0.55
     Haga
    0.55
     mesmos
    0.53
            
    0.52
      
    0.51
     összefoglaló
    0.50
    Activations Density 0.036%

    No Known Activations