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. 4-GEMMASCOPE-RES-16K
    6. 595
    Prev
    Next
    INDEX
    Explanations

    UI elements and button classes in web development 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
    httphttps
    -0.94
    GEBURTSDATUM
    -0.87
    Datuak
    -0.77
    IntoConstraints
    -0.74
     wikipagina
    -0.72
    PhysRev
    -0.71
     StatefulWidget
    -0.69
     >=",
    -0.69
     bezeichneter
    -0.68
     jScrollPane
    -0.67
    POSITIVE LOGITS
    danger
    0.88
    primary
    0.82
     primary
    0.60
    Primary
    0.49
     PNP
    0.49
    Danger
    0.49
    atguigu
    0.49
     REA
    0.48
    ppure
    0.48
    ENR
    0.47
    Activations Density 0.202%

    No Known Activations