© 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. 2-GEMMASCOPE-RES-16K
    11. 12489
    Prev
    Next
    INDEX
    Explanations

    instances of the preposition "at."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     pleaſure
    -0.71
     purpoſe
    -0.70
    leſs
    -0.69
     myſelf
    -0.68
     juſ
    -0.67
     itſelf
    -0.67
     houſe
    -0.66
     anſ
    -0.66
     tranſ
    -0.66
    ſelf
    -0.63
    POSITIVE LOGITS
     at
    2.58
     At
    1.48
    At
    1.41
     tại
    1.18
    at
    1.05
     ở
    0.99
     AT
    0.98
    Tại
    0.92
     Tại
    0.91
     on
    0.87
    Activations Density 0.260%

    No Known Activations