© 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. 10-GEMMASCOPE-RES-16K
    11. 15827
    Prev
    Next
    INDEX
    Explanations

    references to the color blue and its various shades or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
    makeConstraints
    -0.51
    ţiile
    -0.46
    țiile
    -0.43
    minator
    -0.43
     küche
    -0.42
     dź
    -0.41
     lumineuse
    -0.40
    ashian
    -0.40
     Foire
    -0.40
     weights
    -0.40
    POSITIVE LOGITS
     blue
    1.84
     Blue
    1.80
    Blue
    1.74
     BLUE
    1.72
    blue
    1.68
    BLUE
    1.67
     blues
    1.33
    蓝
    1.27
    ブルー
    1.23
     mavi
    1.22
    Activations Density 0.117%

    No Known Activations