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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 16166
    Prev
    Next
    INDEX
    Explanations

    references to the word "they" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pomo
    -0.59
     Thon
    -0.53
     відо
    -0.52
    तः
    -0.49
    ➋
    -0.49
     Hins
    -0.48
     feen
    -0.47
     Rés
    -0.47
     entanto
    -0.47
    odb
    -0.47
    POSITIVE LOGITS
     they
    3.29
    they
    2.71
    They
    2.61
     They
    2.55
     THEY
    2.44
    THEY
    2.38
     они
    1.96
     mereka
    1.78
    Mereka
    1.71
     theyre
    1.69
    Activations Density 0.096%

    No Known Activations