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. 6681
    Prev
    Next
    INDEX
    Explanations

    terms related to document preservation and archival practices

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

    historical documents or records

    np_acts-logits-general · gemini-2.0-flash

    archival records and documents

    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
     مشارکت‌کنندگان
    -0.60
    reportWebVitals
    -0.58
     onOptions
    -0.57
    BrowserModule
    -0.55
    ModelBuilder
    -0.53
    mainAxisSize
    -0.53
     فريبيس
    -0.51
     réglable
    -0.49
     désolés
    -0.48
    antMatchers
    -0.48
    POSITIVE LOGITS
     documents
    1.36
     archives
    1.30
     archive
    1.22
     archival
    1.20
     Documents
    1.18
    documents
    1.16
     Archives
    1.15
     document
    1.12
     archiv
    1.11
     records
    1.11
    Activations Density 0.536%

    No Known Activations