© 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. 3156
    Prev
    Next
    INDEX
    Explanations

    instances of the word "blue" and its variations in various contexts

    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
     typelib
    -0.99
    __":
    -0.94
    reportWebVitals
    -0.91
    Personensuche
    -0.90
     Roskov
    -0.83
     >=",
    -0.82
     kombat
    -0.81
     ostavi
    -0.80
    Παραπομπές
    -0.80
     ainfi
    -0.79
    POSITIVE LOGITS
     Blue
    1.92
     blue
    1.89
     BLUE
    1.85
    Blue
    1.81
    blue
    1.77
    BLUE
    1.72
     blau
    1.35
     blues
    1.35
     azules
    1.32
     Blues
    1.30
    Activations Density 0.021%

    No Known Activations