Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6548
    Prev
    Next
    INDEX
    Explanations

    phrases related to being abandoned or left behind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoresizingMask
    -0.74
     disponibilités
    -0.71
     LoggerFactory
    -0.68
     jScrollPane
    -0.61
     uska
    -0.59
     Reverso
    -0.58
    orex
    -0.57
    الإنجليزية
    -0.57
    нительно
    -0.56
    ParallelGroup
    -0.56
    POSITIVE LOGITS
     unattended
    0.89
     leave
    0.88
     alone
    0.85
    leave
    0.79
    Leave
    0.79
     Leave
    0.78
     leaving
    0.75
     untouched
    0.74
     behind
    0.74
     leaves
    0.70
    Activations Density 0.112%

    No Known Activations