© 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. 16-GEMMASCOPE-RES-16K
    11. 8437
    Prev
    Next
    INDEX
    Explanations

    financial terminology related to investments

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

    Interest rates or financial yields

    np_acts-logits-general · gemini-2.0-flash

    interest rate yield

    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
     Abre
    -0.44
     Res
    -0.43
     etapa
    -0.41
    icestershire
    -0.41
     bio
    -0.40
    bio
    -0.40
     tiến
    -0.39
     elimin
    -0.39
    andro
    -0.39
     Workforce
    -0.38
    POSITIVE LOGITS
    iastes
    0.74
     InputDecoration
    0.72
     depositors
    0.70
    AndEndTag
    0.70
    Boring
    0.66
     safest
    0.65
     boring
    0.65
    ":[{
    0.64
    WebVitals
    0.64
     yield
    0.63
    Activations Density 0.128%

    No Known Activations