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. 24-GEMMASCOPE-RES-16K
    6. 8334
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric or symbolic patterns typically used in data representation or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hexadecimal numbers

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal 0x... assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.62
    UnusedPrivate
    -0.57
    بوابة
    -0.56
    はじめに
    -0.56
     gradova
    -0.52
     дописавши
    -0.47
     mainland
    -0.47
    AsUp
    -0.46
    حياته
    -0.46
     samfun
    -0.46
    POSITIVE LOGITS
     الحره
    0.68
     intptr
    0.65
     שוליים
    0.62
     <<<<<<<<<<<<<<
    0.60
     initComponents
    0.58
     때문
    0.57
     =>
    
    0.55
    awtextra
    0.55
    }{*}{
    0.54
     архивлан
    0.54
    Activations Density 0.137%

    No Known Activations