Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 7669
    Prev
    Next
    INDEX
    Explanations

    the word "while" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 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
    Datuak
    -0.97
     ALF
    -0.84
     SAK
    -0.83
     Lyt
    -0.81
     Eff
    -0.79
     Ayr
    -0.77
    WindowConstants
    -0.76
    Falk
    -0.75
     Seok
    -0.74
     Falk
    -0.74
    POSITIVE LOGITS
     While
    1.08
     while
    1.03
    WHILE
    0.98
     WHILE
    0.97
    while
    0.94
    While
    0.93
     Whilst
    0.89
    Whilst
    0.88
    ilst
    0.85
     whilst
    0.83
    Activations Density 0.063%

    No Known Activations