© 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-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2813
    Prev
    Next
    INDEX
    Explanations

    the word "we" and its variations, indicating a focus on collective identity or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parcelize
    -0.43
    Sucesor
    -0.42
    INSON
    -0.40
     gezet
    -0.39
    enumi
    -0.39
    liferay
    -0.37
    millimeters
    -0.36
     nonUne
    -0.35
    FailureListener
    -0.35
    参考にして
    -0.35
    POSITIVE LOGITS
    we
    2.38
    WE
    2.31
     WE
    2.28
     We
    2.17
    We
    2.06
     we
    1.75
     мы
    1.63
     Мы
    1.37
    Мы
    1.37
    wea
    1.29
    Activations Density 0.406%

    No Known Activations