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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11064
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to medical conditions and study protocols

    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
    FormTagHelper
    -0.80
    الحياه
    -0.70
    GraphicsUnit
    -0.62
    ArgsConstructor
    -0.58
    TagMode
    -0.54
     InputDecoration
    -0.54
    انجليز
    -0.52
    tagHelperRunner
    -0.49
    setVerticalGroup
    -0.47
     BorderSide
    -0.45
    POSITIVE LOGITS
    +:+
    0.74
    engertian
    0.64
     autorytatywna
    0.64
    ArrowToggle
    0.61
    Rüyada
    0.61
    RegressionTest
    0.60
     Commentaires
    0.57
     createState
    0.57
     Throwable
    0.56
     Griechen
    0.56
    Activations Density 0.841%

    No Known Activations