© 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. 0-GEMMASCOPE-RES-16K
    11. 9510
    Prev
    Next
    INDEX
    Explanations

    concepts and actions related to cleaning and environmental maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    curities
    -0.32
    }{$\
    -0.29
    Leben
    -0.29
    anInt
    -0.28
    子上
    -0.27
    ècie
    -0.27
     voren
    -0.27
     Lagu
    -0.27
    illots
    -0.27
     мѣ
    -0.26
    POSITIVE LOGITS
     cleanup
    1.43
     cleaning
    1.41
     demolition
    1.39
     Cleaning
    1.34
     demolish
    1.34
     Cleanup
    1.32
     CLEANING
    1.28
    Cleaning
    1.28
     destroy
    1.24
    cleaning
    1.23
    Activations Density 2.025%

    No Known Activations