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. 10848
    Prev
    Next
    INDEX
    Explanations

    instances of formatting or layout specifications in documents

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

    Tokens preceding "width" or related terms

    np_acts-logits-general · gemini-2.0-flash

    width specification in markup

    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
     kasarigan
    -0.74
    ,:);
    -0.58
    ardless
    -0.56
    пі
    -0.56
    Jeografia
    -0.53
    ']))
    -0.53
    ("-");
    -0.53
    dań
    -0.53
    ("]");
    -0.52
    ']);
    
    -0.52
    POSITIVE LOGITS
     width
    1.41
    width
    1.17
     Width
    1.06
     WIDTH
    0.97
    idth
    0.97
    Width
    0.96
     widths
    0.95
    WIDTH
    0.84
     шири
    0.81
     Breite
    0.80
    Activations Density 0.033%

    No Known Activations