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. 11-GEMMASCOPE-RES-16K
    6. 5674
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values and mathematical notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qrstuvwxyz
    -0.66
    XmlType
    -0.61
    eien
    -0.59
    uent
    -0.56
    writeFileSync
    -0.56
    fjspx
    -0.55
    AccessorTable
    -0.55
     Einfluß
    -0.54
     مواليد
    -0.53
     Erişim
    -0.52
    POSITIVE LOGITS
    enumi
    0.83
    </thead>
    0.80
    Enllaces
    0.71
     aéri
    0.65
    ្
    0.63
     متعلقه
    0.59
    blå
    0.57
    <0xDA>
    0.57
    MockMvc
    0.57
     oreilles
    0.56
    Activations Density 0.569%

    No Known Activations