© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12623
    Prev
    Next
    INDEX
    Explanations

    financial terms and their associated values

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

    Monetary amounts

    np_acts-logits-general · gemini-2.0-flash

    amounts and prices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.38
     haast
    -0.35
    Sucesor
    -0.33
     ventajas
    -0.32
     ventaja
    -0.30
    blur
    -0.29
    ToAction
    -0.29
    赦
    -0.29
     <=",
    -0.27
    actylus
    -0.27
    POSITIVE LOGITS
    kháu
    0.75
    mybatisplus
    0.74
     dollar
    0.70
     money
    0.68
     monetary
    0.68
     price
    0.66
     amount
    0.66
     amounts
    0.65
    金额
    0.63
    金額
    0.63
    Activations Density 0.365%

    No Known Activations