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. 6685
    Prev
    Next
    INDEX
    Explanations

    scientific concepts and terminology related to uncertainty and measurement

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

    Imperative verbs followed by demonstrative pronouns

    np_acts-logits-general · gemini-2.0-flash

    do this or check this

    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
    rungsseite
    -0.62
    HtmlAttribute
    -0.59
    tagHelperRunner
    -0.56
    Хьажоргаш
    -0.54
    bibfield
    -0.52
     Deze
    -0.52
    ("="
    -0.52
    IGraphics
    -0.51
    aarrggbb
    -0.51
     @{
    -0.51
    POSITIVE LOGITS
     isso
    1.93
     cela
    1.61
     ello
    1.55
     eso
    1.52
    这一点
    1.47
     ذلك
    1.38
     esto
    1.29
    这点
    1.28
     это
    1.28
     Isso
    1.25
    Activations Density 0.657%

    No Known Activations