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. 5-GEMMASCOPE-RES-16K
    6. 12287
    Prev
    Next
    INDEX
    Explanations

    instances of the word "please."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.85
    ation
    -0.76
    vB
    -0.75
    UDC
    -0.73
    كويكب
    -0.73
     AspNetCore
    -0.71
     onData
    -0.70
    ATION
    -0.69
    GMENT
    -0.69
     quella
    -0.67
    POSITIVE LOGITS
     please
    1.99
     Please
    1.86
    Please
    1.80
    please
    1.73
     PLEASE
    1.68
    PLEASE
    1.54
     pls
    1.45
    Pls
    1.38
     Pls
    1.33
     Bitte
    1.26
    Activations Density 0.043%

    No Known Activations