© 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. 2-GEMMASCOPE-RES-16K
    11. 4531
    Prev
    Next
    INDEX
    Explanations

    instances of the word "restore" and its variations, indicating a focus on recovery or regaining something that has been lost

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flexible
    -0.41
     flexib
    -0.39
     adults
    -0.39
     Flexib
    -0.38
     uintptr
    -0.38
    toxicity
    -0.37
    flexible
    -0.37
    DotNetBar
    -0.37
     adult
    -0.37
    Flexible
    -0.37
    POSITIVE LOGITS
     restore
    1.03
     Restore
    0.92
     restoration
    0.91
     restoring
    0.91
    restore
    0.88
     restored
    0.87
     warning
    0.84
     restores
    0.84
     Restoration
    0.84
    Restore
    0.79
    Activations Density 0.080%

    No Known Activations