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. 4-GEMMASCOPE-RES-16K
    6. 706
    Prev
    Next
    INDEX
    Explanations

    symbols and operators used in mathematical equations and programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )++;
    -0.76
    ImageContext
    -0.74
    ElementException
    -0.73
    MessageOf
    -0.73
    PreExecute
    -0.60
    JspWriter
    -0.60
    IUrlHelper
    -0.59
    ője
    -0.59
    rzysz
    -0.58
     createState
    -0.58
    POSITIVE LOGITS
    interopRequire
    0.53
     وصلة
    0.52
    таратура
    0.52
    ارتمان
    0.50
    forName
    0.49
    منابع
    0.49
    homonymie
    0.48
    ribusi
    0.47
    DispatchToProps
    0.45
     OFDb
    0.45
    Activations Density 2.605%

    No Known Activations