© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 13607
    Prev
    Next
    INDEX
    Explanations

    financial terms related to corporate negotiations and deals

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

    Preceding Reuters, numbers, or parentheses

    np_acts-logits-general · gemini-2.0-flash

    Reuters financial news

    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
     nahilalakip
    -0.84
    EndContext
    -0.61
    __':
    -0.60
     chân
    -0.56
     Apparently
    -0.56
    SharedDtor
    -0.55
    ICZ
    -0.55
    MemoryWarning
    -0.53
    tten
    -0.52
    ViewInit
    -0.50
    POSITIVE LOGITS
    Reuters
    0.73
     Reuters
    0.64
    reuters
    0.62
     reuters
    0.62
    REUTERS
    0.62
     démission
    0.57
     NgModule
    0.57
    ^^^^^^^^
    0.55
    ❋
    0.54
     Briton
    0.53
    Activations Density 0.052%

    No Known Activations