Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 6326
    Prev
    Next
    INDEX
    Explanations

    concepts related to improvement and operational efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isContained
    -0.86
    IUrlHelper
    -0.84
     myſelf
    -0.77
     مشارکت‌کنندگان
    -0.77
     themſelves
    -0.76
     Monfieur
    -0.75
    Демографія
    -0.71
    таратура
    -0.70
    ScopeManager
    -0.68
    HtmlAttribute
    -0.67
    POSITIVE LOGITS
     những
    0.70
     các
    0.69
    Cuáles
    0.64
    ские
    0.64
     mga
    0.62
     those
    0.59
    ные
    0.58
    ских
    0.58
    льные
    0.57
     these
    0.57
    Activations Density 1.037%

    No Known Activations