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. 16-GEMMASCOPE-RES-16K
    6. 6647
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to trusts and estates

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

    Terms related to wills and estates

    np_acts-logits-general · gemini-2.0-flash

    wills, estates, and probate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.64
    __':
    
    -0.57
     sumpay
    -0.56
     armis
    -0.54
     cancellations
    -0.53
    ghted
    -0.52
     verhe
    -0.51
    cosm
    -0.50
    ฏิ
    -0.49
     outsole
    -0.48
    POSITIVE LOGITS
     probate
    0.89
     testamento
    0.81
     Probate
    0.79
     estate
    0.76
     Estate
    0.70
     Testament
    0.70
     autorytatywna
    0.68
     executor
    0.68
    Estate
    0.66
     executors
    0.65
    Activations Density 0.258%

    No Known Activations