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. 16074
    Prev
    Next
    INDEX
    Explanations

    discussions related to public interest or political topics

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

    before or after dates

    np_acts-logits-general · gemini-2.0-flash

    posted or published dates

    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
    MigrationBuilder
    -0.92
    تقاوى
    -0.81
    :✨
    -0.76
     Waray
    -0.76
     protoimpl
    -0.68
    setVerticalGroup
    -0.68
     nakalista
    -0.68
     فريبيس
    -0.67
    المكان
    -0.67
    webElementXpaths
    -0.66
    POSITIVE LOGITS
    Tags
    0.84
     Categories
    0.77
     admin
    0.76
     posts
    0.75
     tags
    0.74
    Categories
    0.74
     Tags
    0.73
     Category
    0.73
     Posts
    0.71
    Posted
    0.70
    Activations Density 0.470%

    No Known Activations