© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2240
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns and possessives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suivantes
    -0.62
     myſelf
    -0.60
     himſelf
    -0.60
     itſelf
    -0.59
    WebServlet
    -0.59
    נטרנט
    -0.59
    ترنت
    -0.59
     tijden
    -0.58
     econó
    -0.58
     themſelves
    -0.57
    POSITIVE LOGITS
    PreferredItem
    0.78
     own
    0.77
     his
    0.75
    是我的
    0.73
     His
    0.72
     HIS
    0.71
    Whose
    0.71
    itoneal
    0.69
    jspx
    0.69
     their
    0.67
    Activations Density 0.325%

    No Known Activations