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. 4079
    Prev
    Next
    INDEX
    Explanations

    terms and keywords related to enumeration and counting

    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
    ActionBar
    -0.58
     modelAndView
    -0.57
    écial
    -0.55
    cas
    -0.55
     Гри
    -0.54
     Wester
    -0.54
    éviter
    -0.54
     Hartman
    -0.53
     Stä
    -0.53
     näh
    -0.53
    POSITIVE LOGITS
    enumerate
    3.02
     enumerate
    1.19
     propOrder
    1.14
    enumii
    0.97
    PerformLayout
    0.97
    __).
    0.89
    NamedQueries
    0.87
    Enumerated
    0.86
    displayquote
    0.85
     enumeration
    0.83
    Activations Density 0.029%

    No Known Activations