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. 20-GEMMASCOPE-RES-16K
    6. 5227
    Prev
    Next
    INDEX
    Explanations

    phrases related to shipping policies and customer service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by punctuation or prepositions

    np_acts-logits-general · gemini-2.0-flash

    please, prosím, Bitte

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reszcie
    -1.06
    ftagPool
    -0.81
     Apalagi
    -0.74
     Schließlich
    -0.74
     immerhin
    -0.74
     addirittura
    -0.74
    anskje
    -0.73
     pourtant
    -0.70
     przecież
    -0.70
     NDEBUG
    -0.70
    POSITIVE LOGITS
     prosím
    1.00
     please
    0.97
     Please
    0.85
    Please
    0.79
     PLEASE
    0.76
    PLEASE
    0.71
    please
    0.71
     vui
    0.70
     कृपया
    0.70
    Bitte
    0.70
    Activations Density 0.526%

    No Known Activations