© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2649
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and calculations

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

    sequences of mathematical terms

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    undum
    -0.47
    二十四
    -0.44
    map
    -0.41
     XXII
    -0.41
    Libra
    -0.40
    ë
    -0.40
    orance
    -0.38
    rizona
    -0.37
    Luna
    -0.37
     XXIV
    -0.37
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.81
    uxxxx
    0.70
    KommentareTeilen
    0.70
    IndentedString
    0.67
    ServletException
    0.66
    ManagedBean
    0.66
    onViewCreated
    0.66
     initComponents
    0.65
    OrNil
    0.65
    WaitGroup
    0.63
    Activations Density 0.369%

    No Known Activations