© 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. 6-GEMMASCOPE-RES-16K
    11. 12731
    Prev
    Next
    INDEX
    Explanations

    the repetitive use of the word "there."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -1.17
     мәкал
    -1.07
     autorytatywna
    -1.04
    
    -0.98
    SharedCtor
    -0.98
     للمعارف
    -0.91
    Geplaatst
    -0.89
     CURIAM
    -0.87
     Cæsar
    -0.86
    Lähteet
    -0.84
    POSITIVE LOGITS
     there
    1.30
     There
    1.26
    There
    1.22
    there
    1.12
    THERE
    0.93
     no
    0.89
     THERE
    0.84
     are
    0.78
     existi
    0.72
     a
    0.71
    Activations Density 0.083%

    No Known Activations