© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 2480
    Prev
    Next
    INDEX
    Explanations

    indications of statistical performance metrics in a programmatic context

    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
     समीक्षक
    -0.58
    клопе
    -0.54
     StatefulWidget
    -0.54
     Quay
    -0.53
    ekwondo
    -0.52
    Suspense
    -0.52
    SQU
    -0.51
     UITableView
    -0.51
     lot
    -0.48
     Zol
    -0.48
    POSITIVE LOGITS
    UserScript
    0.72
    SequentialGroup
    0.71
    脚注の使い方
    0.68
    Personensuche
    0.66
    deepcopy
    0.66
    ChildScrollView
    0.63
     nahilalakip
    0.61
    GEBURTSDATUM
    0.60
    новниш
    0.59
    Portale
    0.58
    Activations Density 0.362%

    No Known Activations