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. 4699
    Prev
    Next
    INDEX
    Explanations

    structural indicators of the start of a document or section within the text

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

    Code snippets and special characters

    np_acts-logits-general · gemini-2.0-flash

    restoration plugin material

    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
    openqa
    -0.46
     noDo
    -0.46
    zzleHttp
    -0.45
     nahilalakip
    -0.44
    <eos>
    -0.42
     فريبيس
    -0.42
     EconPapers
    -0.42
    tagHelperRunner
    -0.42
    ecore
    -0.42
    databind
    -0.40
    POSITIVE LOGITS
     @"/
    0.91
    expandindo
    0.76
    HomeAsUpEnabled
    0.75
     Савезне
    0.74
    httphttps
    0.73
    Хьажоргаш
    0.73
     Мексичка
    0.72
    الإنجليزية
    0.69
    NUMX
    0.68
    <bos>
    0.67
    Activations Density 0.103%

    No Known Activations