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. 12491
    Prev
    Next
    INDEX
    Explanations

    nutritional content and health benefits of food

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

    ingredients and nutritional content

    np_acts-logits-general · gemini-2.0-flash

    containing or including

    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
    BeginInit
    -0.59
    astie
    -0.55
    TagHelpers
    -0.52
     ejac
    -0.50
    prior
    -0.48
    tldr
    -0.48
     TextAppearance
    -0.48
    bekistan
    -0.47
     thái
    -0.47
     }^{[
    -0.47
    POSITIVE LOGITS
    VersionUID
    0.78
     enthalten
    0.66
    indd
    0.61
    ưu
    0.59
    ActionCreators
    0.59
    पया
    0.59
    含ま
    0.57
    SequentialGroup
    0.56
    ųjų
    0.55
     содержа
    0.55
    Activations Density 0.844%

    No Known Activations