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. 12-GEMMASCOPE-RES-16K
    6. 12400
    Prev
    Next
    INDEX
    Explanations

    technical terms related to chemical and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -1.02
     beginnetje
    -0.86
     autorytatywna
    -0.83
     mergeFrom
    -0.82
    makeConstraints
    -0.81
    errHandler
    -0.81
    webElementXpaths
    -0.81
    rénées
    -0.79
     otomatig
    -0.79
     typelib
    -0.79
    POSITIVE LOGITS
    {~
    1.08
     Hewitt
    0.71
    โ
    0.71
    wisata
    0.66
     cartas
    0.64
    orking
    0.63
    {
    0.63
     Korn
    0.63
    سى
    0.62
     dibuka
    0.61
    Activations Density 0.030%

    No Known Activations