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. 11582
    Prev
    Next
    INDEX
    Explanations

    technical terms related to event handling and timers

    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
     ostavi
    -0.72
     ſever
    -0.68
    IsContent
    -0.65
     fevere
    -0.63
     Efq
    -0.62
    belea
    -0.61
     purpoſe
    -0.61
     myſelf
    -0.61
     ſmall
    -0.60
    wiſe
    -0.59
    POSITIVE LOGITS
     nahilalakip
    0.87
    Ifc
    0.54
    الإنجليزية
    0.50
     colectiva
    0.49
    Véxase
    0.49
    TypeDef
    0.48
     elseif
    0.48
    id
    0.48
     renseignements
    0.47
    Atsauces
    0.47
    Activations Density 0.557%

    No Known Activations