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. 18-GEMMASCOPE-RES-16K
    6. 10565
    Prev
    Next
    INDEX
    Explanations

    phrases related to email notifications and confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.75
    出版年
    -0.74
    IntoConstraints
    -0.73
    Tembelea
    -0.73
     Vikipedi
    -0.73
     noqa
    -0.72
    tvguidetime
    -0.71
     viewDidLoad
    -0.65
    Портал
    -0.64
     Paglinawan
    -0.63
    POSITIVE LOGITS
     confirmation
    0.73
     confirm
    0.65
    confirmation
    0.62
     propOrder
    0.62
    Confirmation
    0.61
     Confirmation
    0.61
     Confirm
    0.57
     confirming
    0.55
    Confirm
    0.53
     confirma
    0.53
    Activations Density 0.225%

    No Known Activations