© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    structured data representations, specifically related to programming or markup languages

    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
     >=",
    -1.10
    ValueStyle
    -0.98
    setVerticalGroup
    -0.93
    expandindo
    -0.91
     purpoſe
    -0.83
     Савезне
    -0.83
     Monfieur
    -0.82
     myſelf
    -0.82
     uſed
    -0.80
     Theſe
    -0.79
    POSITIVE LOGITS
    </strong>
    0.53
    ”
    0.44
     Double
    0.44
    (
    0.43
     i
    0.42
     pre
    0.41
    &
    0.41
    енча
    0.41
     ddelweddau
    0.41
     traditional
    0.40
    Activations Density 2.970%

    No Known Activations