© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104284
    Prev
    Next
    INDEX
    Explanations

    the word "robust" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     filler
    -0.43
    thay
    -0.42
     getItemId
    -0.42
    Insertion
    -0.40
    eye
    -0.40
     Ticket
    -0.40
    CompilerServices
    -0.39
     Center
    -0.39
     Intersection
    -0.39
     year
    -0.39
    POSITIVE LOGITS
    robust
    1.06
     Robust
    1.05
     robust
    1.05
    Robust
    1.05
     robustness
    0.87
     robuste
    0.85
     robusto
    0.81
     robus
    0.80
    ggish
    0.70
     resilient
    0.69
    Activations Density 0.006%

    No Known Activations