© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 107525
    Prev
    Next
    INDEX
    Explanations

    references to the word "Mercury" and its related associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opsis
    -0.47
    nof
    -0.47
    Socio
    -0.44
     Parton
    -0.44
     Parti
    -0.44
    Fold
    -0.43
     Socio
    -0.43
     tif
    -0.43
    Atta
    -0.42
    filet
    -0.42
    POSITIVE LOGITS
     Mercury
    1.22
    Mercury
    1.19
     mercury
    1.05
    mercury
    1.02
    CURY
    0.91
     Hg
    0.90
     Mercu
    0.81
    Hg
    0.77
     Mercurio
    0.68
     mercu
    0.67
    Activations Density 0.010%

    No Known Activations