© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 2147
    Prev
    Next
    INDEX
    Explanations

    elements related to chart layout and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.90
    }}]{
    -0.84
     pleaſure
    -0.82
     ainfi
    -0.82
    ]**
    -0.80
    ViewImports
    -0.80
    windowFixed
    -0.80
     CommonModule
    -0.76
     Wikispecies
    -0.74
    Citiți
    -0.74
    POSITIVE LOGITS
    Chart
    0.91
     transport
    0.86
     Chart
    0.78
     transportation
    0.73
     Transport
    0.71
    ه
    0.70
    chart
    0.68
     Law
    0.65
    transport
    0.63
     Transportation
    0.63
    Activations Density 0.302%

    No Known Activations