© 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. 3512
    Prev
    Next
    INDEX
    Explanations

    items related to financial transactions and accounting records

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

    Accounting or financial records

    np_acts-logits-general · gemini-2.0-flash

    financial journal entries

    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
    ExtendWith
    -0.54
     fittest
    -0.50
    tableFuture
    -0.49
     disambiguazione
    -0.49
    MetaType
    -0.47
    numerusform
    -0.47
    allis
    -0.46
     StringTokenizer
    -0.46
     SIAM
    -0.45
     protoimpl
    -0.45
    POSITIVE LOGITS
     journal
    0.81
    journal
    0.66
     recording
    0.64
    journals
    0.64
     Journal
    0.64
    bited
    0.63
     journals
    0.63
     JOURNAL
    0.62
    Journal
    0.62
    setVerticalGroup
    0.59
    Activations Density 0.121%

    No Known Activations