© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8541
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize cleanliness or cleanliness-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
     immobilier
    -0.88
    rungsseite
    -0.84
     avoient
    -0.81
    المناصب
    -0.79
     متعلقه
    -0.79
    Personensuche
    -0.78
     termica
    -0.78
     Tomlinson
    -0.76
    bited
    -0.75
    IBOutlet
    -0.75
    POSITIVE LOGITS
     clean
    3.19
     Clean
    3.06
     CLEAN
    2.91
    clean
    2.89
    Clean
    2.87
    CLEAN
    2.54
     cleans
    2.26
     cleaner
    2.22
     cleaned
    2.08
     cleanest
    2.02
    Activations Density 0.031%

    No Known Activations