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. 14435
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and syntax related to functions and equations

    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
    EndContext
    -0.56
     Majefty
    -0.54
     pesce
    -0.53
     ejus
    -0.52
     VizieR
    -0.50
     quæ
    -0.49
     mocht
    -0.49
     Uncategorized
    -0.49
    RuleContext
    -0.48
     nodig
    -0.48
    POSITIVE LOGITS
     disponibilités
    1.02
    ))){
    0.70
    Geplaatst
    0.68
    ))).
    0.66
    QMetaType
    0.63
    DockStyle
    0.63
     оригіналу
    0.62
     utafitiHapana
    0.62
    出版年
    0.61
    vereignty
    0.61
    Activations Density 0.490%

    No Known Activations