© 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 EvalsExportsAPI 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. 15661
    Prev
    Next
    INDEX
    Explanations

    terms related to property tax and its implications

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

    "tax" or "assessment"

    np_acts-logits-general · gemini-2.0-flash

    property tax assessment

    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
    Демографія
    -0.66
     كومونز
    -0.58
    tagHelperRunner
    -0.54
     actionMode
    -0.54
    XmlAccessorType
    -0.53
    melte
    -0.47
    icolo
    -0.47
    رافی
    -0.47
     volcán
    -0.47
     skri
    -0.45
    POSITIVE LOGITS
     tax
    1.26
     taxes
    1.19
     taxation
    1.14
     taxed
    1.10
    Tax
    1.05
     Tax
    1.05
    tax
    1.04
     TAX
    1.03
     taxable
    1.03
     taxing
    1.01
    Activations Density 0.103%

    No Known Activations