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. 550
    Prev
    Next
    INDEX
    Explanations

    instances of brackets or similar structures in mathematical equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     appart
    -0.57
    slidesToShow
    -0.57
    InputBorder
    -0.53
     invokevirtual
    -0.50
     lever
    -0.50
    GraphicsUnit
    -0.49
     />\
    -0.48
    lacian
    -0.48
     transfieras
    -0.47
    ाद
    -0.47
    POSITIVE LOGITS
    enumii
    0.74
    cc
    0.69
    structors
    0.64
    enumi
    0.64
    expandindo
    0.63
    __":
    0.61
    findpost
    0.60
    httphttps
    0.59
    Referències
    0.58
    *{
    0.58
    Activations Density 0.038%

    No Known Activations