© 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. 8593
    Prev
    Next
    INDEX
    Explanations

    names of individuals and references to events or relationships

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

    Followed by punctuation or a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    technical classification codes

    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
     such
    -0.53
    BufferException
    -0.51
     analyzed
    -0.49
    epam
    -0.47
    ustomed
    -0.46
    FilterChain
    -0.46
    ppus
    -0.45
     détaillée
    -0.44
     major
    -0.43
     Multi
    -0.43
    POSITIVE LOGITS
    adaptiveStyles
    0.79
    QMetaType
    0.74
    RenderAtEndOf
    0.72
     препратки
    0.72
    RegressionTest
    0.69
    पया
    0.69
    Autoritní
    0.67
     autorytatywna
    0.67
     AssemblyCulture
    0.66
    EndGlobalSection
    0.63
    Activations Density 0.051%

    No Known Activations