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. 5-GEMMASCOPE-RES-16K
    6. 11671
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AfterViewInit
    -0.63
     Мексичка
    -0.58
    tagHelperRunner
    -0.57
    Sucesor
    -0.57
    ⎨
    -0.56
     Lordships
    -0.56
     Jefus
    -0.56
     abbraccio
    -0.55
    annica
    -0.55
     greateſt
    -0.55
    POSITIVE LOGITS
    PreferredItem
    0.66
     الدولى
    0.66
    rrggbb
    0.62
    hyrchwyd
    0.58
    TintMode
    0.56
    ValueStyle
    0.52
     समीक्षाओं
    0.51
     Bed
    0.51
    println
    0.50
    PYX
    0.50
    Activations Density 0.792%

    No Known Activations