© 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. 20-GEMMASCOPE-RES-16K
    11. 4056
    Prev
    Next
    INDEX
    Explanations

    structures related to mathematical arrays or matrices

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

    Mathematical arrays/matrices

    np_acts-logits-general · gemini-2.0-flash

    array followed by brace

    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
    enderror
    -0.72
    endpush
    -0.72
     متعلقه
    -0.55
    DockStyle
    -0.53
     })}
    -0.52
    '])->
    -0.48
    LookAnd
    -0.47
     Reaktion
    -0.45
    ))));
    -0.45
     kasarigan
    -0.44
    POSITIVE LOGITS
    पया
    0.71
    клопе
    0.69
    makeConstraints
    0.68
    GEBURTSDATUM
    0.61
    AccessorTable
    0.60
     linkovi
    0.56
     propOrder
    0.55
    IntoConstraints
    0.55
    DotNetBar
    0.55
    usehen
    0.55
    Activations Density 0.061%

    No Known Activations