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. 16-GEMMASCOPE-RES-16K
    6. 12674
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "are" in relation to various subjects and contexts

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

    "are" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    linking verb followed by description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.73
     pouvoirs
    -0.61
    HandlerContext
    -0.60
     Fras
    -0.60
    ţilor
    -0.60
     nytt
    -0.60
     itself
    -0.59
     Itself
    -0.59
    дів
    -0.59
     mellitus
    -0.59
    POSITIVE LOGITS
     themselves
    1.11
    themselves
    0.97
     are
    0.95
     yourselves
    0.88
    wolves
    0.86
     were
    0.84
     voltak
    0.80
     eds
    0.77
     ARE
    0.77
    preduce
    0.74
    Activations Density 0.515%

    No Known Activations