© 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-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10837
    Prev
    Next
    INDEX
    Explanations

    financial metrics and economic indicators related to unemployment and inflation

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

    Percentages and numerical values

    np_acts-logits-general · gemini-2.0-flash

    detecting percentages and rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.44
    WriteTagHelper
    -0.43
    MLLoader
    -0.42
    IBar
    -0.40
     IActionResult
    -0.39
    €)
    -0.37
     "'",
    -0.36
     PeEnEo
    -0.36
     lisboa
    -0.36
    ">//
    -0.36
    POSITIVE LOGITS
     percentage
    1.07
     percentages
    0.97
     percent
    0.92
     (%)
    0.88
     pourcentage
    0.87
    percentage
    0.86
     Percentage
    0.82
     (\%)
    0.79
     porcentaje
    0.77
    (%)
    0.77
    Activations Density 0.625%

    No Known Activations