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

    Neuronpedia

    APICircuit 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. 15-GEMMASCOPE-RES-16K
    6. 2420
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ALF
    -0.77
    رفة
    -0.75
     Lyt
    -0.75
     Cæsar
    -0.75
    Falk
    -0.74
    Datuak
    -0.74
     Toma
    -0.73
     SAK
    -0.72
     Akismet
    -0.71
     Falk
    -0.70
    POSITIVE LOGITS
     while
    0.92
     While
    0.90
    ilst
    0.82
     WHILE
    0.82
     the
    0.81
     Enquanto
    0.79
    WHILE
    0.78
     whilst
    0.78
    География
    0.77
     Whilst
    0.76
    Activations Density 0.076%

    No Known Activations