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. 20-GEMMASCOPE-RES-16K
    6. 7681
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" in various contexts

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

    Follows "as a" (or "as")

    np_acts-logits-general · gemini-2.0-flash

    as a result/consequence/precaution

    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
    больше
    -0.52
    Plenty
    -0.51
    MLLoader
    -0.50
     élevées
    -0.45
    こと
    -0.45
    /**
    -0.44
     plenty
    -0.43
    בש
    -0.43
    kto
    -0.43
    リーム
    -0.43
    POSITIVE LOGITS
     result
    1.28
     consequence
    0.99
    result
    0.95
     resultado
    0.90
     precaution
    0.89
     matter
    0.85
     resultat
    0.83
     part
    0.82
    ngdoc
    0.81
     فريبيس
    0.80
    Activations Density 0.112%

    No Known Activations