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. 2088
    Prev
    Next
    INDEX
    Explanations

    elements related to significant characters or themes in narratives

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

    preceding "*Trametes versicolor*"

    np_acts-logits-general · gemini-2.0-flash

    HM Revenue

    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
    CodeAttribute
    -0.80
     høre
    -0.56
     تعدى
    -0.54
     Riproduzione
    -0.53
    remadura
    -0.53
    Viited
    -0.53
    ckeye
    -0.52
     communiquer
    -0.52
    msgTypes
    -0.51
    Pautan
    -0.50
    POSITIVE LOGITS
     Himo
    0.78
    mable
    0.78
    mers
    0.71
    geddon
    0.69
    mi
    0.64
    selfish
    0.64
     ***!
    0.63
    thyst
    0.63
    mmm
    0.62
     HEM
    0.62
    Activations Density 1.333%

    No Known Activations