© 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. 18-GEMMASCOPE-RES-16K
    11. 2554
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions and economic impacts relating to money management

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

    Money being allocated, used, or spent

    np_acts-logits-general · gemini-2.0-flash

    spending and putting money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ৃ
    -0.46
    ograph
    -0.45
     Mer
    -0.44
     mit
    -0.42
    setPreferred
    -0.42
     Ham
    -0.42
    torie
    -0.41
     favored
    -0.41
     minst
    -0.41
    строен
    -0.41
    POSITIVE LOGITS
     spent
    1.00
     invested
    0.87
     typelib
    0.79
     expended
    0.78
    spent
    0.78
     spend
    0.73
     allocated
    0.73
     collected
    0.72
     Spent
    0.72
     dépens
    0.71
    Activations Density 0.415%

    No Known Activations