© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9942
    Prev
    Next
    INDEX
    Explanations

    references to budget, spending, and financial management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jooq
    -0.72
     jLabel
    -0.68
    lwjgl
    -0.67
    Occurrences
    -0.65
     onlyOwner
    -0.64
    /*---
    -0.62
     '{@
    -0.62
     /\.(
    -0.61
    enderror
    -0.60
     ReactDOM
    -0.60
    POSITIVE LOGITS
     budget
    3.51
     Budget
    3.14
    Budget
    3.00
    budget
    2.98
     budgets
    2.87
     BUDGET
    2.84
     Budgets
    2.57
    BUDGET
    2.52
     budgetary
    2.32
     budgeting
    2.32
    Activations Density 0.036%

    No Known Activations