© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 64092
    Prev
    Next
    INDEX
    Explanations

    currency values and transactions

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

    currency amounts

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ammans
    -0.34
     hoort
    -0.34
    </thead>
    -0.33
    wakili
    -0.33
     colorear
    -0.31
     udrž
    -0.31
    Iglesia
    -0.31
    SuppressLint
    -0.31
    めでとう
    -0.30
    füh
    -0.30
    POSITIVE LOGITS
     dollars
    0.84
    dollars
    0.82
     rupees
    0.77
     kroner
    0.75
     Dollars
    0.73
     euros
    0.70
     Pounds
    0.67
    évaluateur
    0.66
     francs
    0.66
     money
    0.65
    Activations Density 0.005%

    No Known Activations