© 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. 18-GEMMASCOPE-RES-16K
    11. 9406
    Prev
    Next
    INDEX
    Explanations

    financial market indices and their fluctuations

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

    preceding "Index" or "Indices"

    np_acts-logits-general · gemini-2.0-flash

    medical scores and indices

    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
    itoria
    -0.46
    脚注の使い方
    -0.46
     оригіналу
    -0.43
    뀐
    -0.43
     وتسجيلات
    -0.43
     AppModule
    -0.41
    dua
    -0.41
    перь
    -0.41
     دیکھیے
    -0.40
     Agencia
    -0.40
    POSITIVE LOGITS
     index
    1.21
     Index
    1.07
     indexes
    1.06
     indices
    1.05
    index
    0.97
     INDEX
    0.95
    Index
    0.92
     índice
    0.91
     composite
    0.89
     indeks
    0.89
    Activations Density 0.237%

    No Known Activations