© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5446
    Prev
    Next
    INDEX
    Explanations

    symbols and typographical elements commonly found in coding, especially parentheses and errors

    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
    原始内容存档于
    -0.64
    tinggi
    -0.52
    archiviato
    -0.48
    ایز
    -0.47
    tierung
    -0.43
    lijks
    -0.43
    hören
    -0.43
    createTextNode
    -0.42
     تعالى
    -0.41
     ?
    -0.41
    POSITIVE LOGITS
    uxxxx
    0.83
    AutoScaleMode
    0.77
     gynnwys
    0.75
    WebpackPlugin
    0.74
    Geplaatst
    0.72
     pinulongan
    0.70
    SpringBootTest
    0.69
    xase
    0.68
    érape
    0.67
    keyColumn
    0.67
    Activations Density 0.821%

    No Known Activations