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. 3-GEMMASCOPE-RES-16K
    6. 11123
    Prev
    Next
    INDEX
    Explanations

    terms related to various roles and responsibilities in professions, especially in the context of education and healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roek
    -0.62
    SequentialGroup
    -0.61
    ูล
    -0.60
    iastical
    -0.57
     ویکی‌پدیا
    -0.56
    mored
    -0.56
     esternos
    -0.54
     otomatig
    -0.54
    igg
    -0.53
    grun
    -0.53
    POSITIVE LOGITS
    ReusableCell
    0.70
    HasForeignKey
    0.68
    MessageTagHelper
    0.57
    autant
    0.57
     hearers
    0.54
    +:+
    0.53
     stabilité
    0.53
    getContentPane
    0.52
     bawat
    0.51
     فريبيس
    0.51
    Activations Density 0.770%

    No Known Activations