© 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. 832
    Prev
    Next
    INDEX
    Explanations

    the pronoun 'we' and related phrases emphasizing collective action or perspective

    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
    LEncoder
    -0.56
     OTHERWISE
    -0.50
     Cuth
    -0.48
     переписи
    -0.47
    measures
    -0.47
     mittleren
    -0.46
    way
    -0.46
     acel
    -0.45
     Function
    -0.45
    jeen
    -0.45
    POSITIVE LOGITS
     autorytatywna
    1.08
    RegistryLite
    0.92
     تضيفلها
    0.91
    protoimpl
    0.72
    romas
    0.72
     MyBatis
    0.67
     سكانية
    0.67
     internetowa
    0.67
    SharedCtor
    0.67
    ",&
    0.66
    Activations Density 0.507%

    No Known Activations