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. 5-GEMMASCOPE-RES-16K
    6. 11246
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming concepts and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TableColumn
    -0.89
     DriverManager
    -0.84
    skrä
    -0.82
    quelize
    -0.78
    //
    -0.78
     sequelize
    -0.75
     ➢
    -0.75
     تضيفلها
    -0.74
    aarrggbb
    -0.74
     onResponse
    -0.74
    POSITIVE LOGITS
    ting
    1.12
    ttt
    1.07
    tttt
    1.03
    tt
    1.00
    thet
    0.97
    tet
    0.96
    tut
    0.91
    lit
    0.88
     rit
    0.86
    at
    0.85
    Activations Density 4.050%

    No Known Activations