© 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. 3-GEMMASCOPE-RES-16K
    11. 8623
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Gra" and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.50
     resourceCulture
    -0.43
    циони
    -0.42
    asymp
    -0.41
    inigte
    -0.40
    Parameteri
    -0.40
    prefixer
    -0.40
    蚪
    -0.40
    testens
    -0.39
    WebVitals
    -0.39
    POSITIVE LOGITS
     gra
    3.20
     Gra
    3.19
    Gra
    3.09
    gra
    2.94
     GRA
    2.23
    GRA
    2.09
     гра
    1.88
     Гра
    1.78
     Graff
    1.74
     GRAV
    1.73
    Activations Density 0.787%

    No Known Activations