© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8866
    Prev
    Next
    INDEX
    Explanations

    a specific structural token indicating the beginning of a new input or section

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

    Mathematical and programming code snippets

    np_acts-logits-general · gemini-2.0-flash

    are mainly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.92
     كومونز
    -0.92
     calendriers
    -0.85
    WithIOException
    -0.81
    InitVars
    -0.79
    complexContent
    -0.78
    ArrowToggle
    -0.78
     Himo
    -0.77
    شهاد
    -0.76
    QMetaType
    -0.75
    POSITIVE LOGITS
    includegraphics
    0.90
    <eos>
    0.70
    ↵↵
    0.63
    ↵
    0.57
    ↵↵↵
    0.51
    ↵↵↵↵
    0.50
     perfusion
    0.48
    View
    0.46
    @
    0.46
        
    0.45
    Activations Density 0.005%

    No Known Activations