© 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. 22-GEMMASCOPE-RES-16K
    11. 9500
    Prev
    Next
    INDEX
    Explanations

    terms related to insurance coverage and policy limits

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

    insurance policies or settlements

    np_acts-logits-general · gemini-2.0-flash

    insurance policy details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jail
    -0.49
    therford
    -0.44
    Clik
    -0.44
    CommandText
    -0.43
    RegressionTest
    -0.42
     поко
    -0.42
    Teknik
    -0.42
     Roskov
    -0.41
     alkaloids
    -0.41
    arXiv
    -0.41
    POSITIVE LOGITS
     insurance
    2.52
     Insurance
    2.11
    insurance
    2.07
    Insurance
    2.03
     insured
    1.91
     INSURANCE
    1.88
     insuring
    1.71
     coverage
    1.69
     insurers
    1.68
     insur
    1.68
    Activations Density 0.184%

    No Known Activations