© 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. 10-GEMMASCOPE-RES-16K
    11. 15891
    Prev
    Next
    INDEX
    Explanations

    expressions of emphasis or intensity, particularly with the word "quite."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     culturelles
    -0.83
     Flanagan
    -0.74
     Krueger
    -0.73
    Bermuda
    -0.73
     Kearney
    -0.72
     layer
    -0.71
     Magdeburg
    -0.69
     Dooley
    -0.66
    gdx
    -0.65
     “
    -0.65
    POSITIVE LOGITS
     quite
    1.26
    quite
    1.25
     Quite
    1.11
    Quite
    1.09
    CloseOperation
    0.91
     uite
    0.84
     تضيفلها
    0.83
    IVEREF
    0.83
     Audiodateien
    0.83
     Fairly
    0.82
    Activations Density 0.064%

    No Known Activations