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. 1741
    Prev
    Next
    INDEX
    Explanations

    present tense and past tense verbs related to formal studies and their descriptions

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

    "is" followed by purpose/intention

    np_acts-logits-general · gemini-2.0-flash

    stating purpose

    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
    IndentedString
    -0.91
     ویکی‌پدیا
    -0.86
     betweenstory
    -0.77
    IContainer
    -0.74
    MethodManager
    -0.73
     bezeichneter
    -0.71
     समीक्षाओं
    -0.71
     SqlParameter
    -0.71
    ChromeDriver
    -0.70
     ModelExpression
    -0.68
    POSITIVE LOGITS
     intended
    0.86
     aimed
    0.82
     based
    0.74
     destinées
    0.72
     destiné
    0.70
     meant
    0.69
     bertujuan
    0.68
     destinée
    0.66
     part
    0.65
     посвя
    0.65
    Activations Density 0.499%

    No Known Activations