Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 12867
    Prev
    Next
    INDEX
    Explanations

    terms related to insurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ALLEL
    -0.80
     Devan
    -0.79
     Callum
    -0.76
    zegor
    -0.75
     Twit
    -0.74
     Parthen
    -0.73
    thand
    -0.72
     Centrale
    -0.72
    SetBool
    -0.72
    раздо
    -0.71
    POSITIVE LOGITS
     Ins
    1.10
     insurance
    1.08
     insur
    1.08
     Insurance
    1.07
    Insurance
    1.02
     INSURANCE
    0.95
     INS
    0.94
    ButterKnife
    0.92
    Ins
    0.92
    insurance
    0.90
    Activations Density 0.188%

    No Known Activations