© 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. 14-GEMMASCOPE-RES-16K
    11. 8307
    Prev
    Next
    INDEX
    Explanations

    instances of the word "clean" and its variations, indicating a focus on cleanliness and cleanliness-related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     valueForKey
    -0.51
    lotz
    -0.47
     symbol
    -0.46
     personage
    -0.46
     moment
    -0.46
     getGroup
    -0.46
     figure
    -0.46
     getArguments
    -0.44
     third
    -0.44
     server
    -0.44
    POSITIVE LOGITS
    Clean
    1.30
     Clean
    1.27
     CLEAN
    1.25
    clean
    1.22
     Cleaner
    1.17
    Cleaning
    1.16
    CLEAN
    1.15
     Cleaning
    1.13
    cleaned
    1.12
    Cleaner
    1.12
    Activations Density 0.080%

    No Known Activations