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. 7398
    Prev
    Next
    INDEX
    Explanations

    references to news outlets and their reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ScopeManager
    -0.82
     оригіналу
    -0.69
    Obrázky
    -0.65
    ParallelGroup
    -0.58
    ChildIndex
    -0.58
    TRAILING
    -0.55
    InputBorder
    -0.55
    ViewImports
    -0.53
    gesamt
    -0.53
    npmjs
    -0.52
    POSITIVE LOGITS
     reporter
    0.83
     magazine
    0.82
     reported
    0.77
     reporting
    0.76
     newspaper
    0.74
     columnist
    0.71
     reports
    0.70
     report
    0.70
    Magazine
    0.67
     publication
    0.67
    Activations Density 0.200%

    No Known Activations