© 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. 3-GEMMASCOPE-RES-16K
    11. 5691
    Prev
    Next
    INDEX
    Explanations

    references to personal pronouns, particularly focusing on expressions of self-identity and perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     your
    -0.91
     you
    -0.86
    your
    -0.81
     yourself
    -0.81
     Your
    -0.81
    you
    -0.75
     You
    -0.74
    Your
    -0.73
     Bạn
    -0.70
    DataAnnotations
    -0.69
    POSITIVE LOGITS
    ocino
    0.68
     AssemblyVersion
    0.60
     ویکی‌پدیا
    0.54
     مواليد
    0.54
     Wicidata
    0.53
    setPreferred
    0.52
     midwives
    0.52
     MyBatis
    0.52
    sidemargin
    0.51
    RepeatedField
    0.51
    Activations Density 0.115%

    No Known Activations