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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 2012
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal requirements and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -0.97
    GEBURTSDATUM
    -0.95
    contentLoaded
    -0.93
    findpost
    -0.86
    !*\
    -0.85
    DeleteBehavior
    -0.80
     allAfrica
    -0.80
    MLLoader
    -0.80
    EDEFAULT
    -0.77
    Geplaatst
    -0.77
    POSITIVE LOGITS
    不需要
    0.78
    无需
    0.75
    只需要
    0.62
    不用
    0.61
    只要
    0.60
    只需
    0.58
     worry
    0.57
     nemus
    0.55
     basta
    0.55
    不必
    0.55
    Activations Density 0.325%

    No Known Activations