© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14881
    Prev
    Next
    INDEX
    Explanations

    terms related to tax liabilities and financial obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ausz
    -0.37
    GTCX
    -0.36
    ymce
    -0.34
    StackNavigator
    -0.34
     Pill
    -0.34
    fü
    -0.33
    烷
    -0.32
     Sho
    -0.32
     Fü
    -0.31
     pill
    -0.31
    POSITIVE LOGITS
     overdue
    1.13
     arrears
    1.10
     delinquent
    1.02
     owed
    1.02
     unpaid
    0.99
     defaulted
    0.95
     collections
    0.86
     outstanding
    0.85
    Outstanding
    0.84
     delinquency
    0.83
    Activations Density 0.662%

    No Known Activations