© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 12962
    Prev
    Next
    INDEX
    Explanations

    references to the letter "W" followed by different characters, suggesting it detects elements related to the letter "W" or its associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoresizingMask
    -0.73
     InputDecoration
    -0.69
    PRNewswire
    -0.64
    addPreferredGap
    -0.59
    warning
    -0.57
    WindowConstants
    -0.55
     warning
    -0.55
    — 
    -0.55
     wedding
    -0.55
     weighted
    -0.55
    POSITIVE LOGITS
    drawal
    0.55
     Wednesdays
    0.54
    ніципалі
    0.52
     WPS
    0.51
     relâche
    0.49
     Kenobi
    0.48
     Allegretto
    0.48
     Warriors
    0.48
    diali
    0.47
    NESDAY
    0.47
    Activations Density 0.596%

    No Known Activations