© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13892
    Prev
    Next
    INDEX
    Explanations

    words related to payment and financial transactions

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

    ending in "ment" or "MENT"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ment

    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
     dieux
    -0.59
    blå
    -0.59
     auroit
    -0.55
     aéro
    -0.53
     Și
    -0.52
     pères
    -0.51
     Inscrivez
    -0.51
     fidé
    -0.51
     âmes
    -0.50
     fédé
    -0.50
    POSITIVE LOGITS
    vement
    0.87
    nement
    0.83
    agement
    0.83
    mmation
    0.82
    tlement
    0.81
    sement
    0.80
    ishment
    0.80
    ment
    0.80
    urement
    0.78
    EMENT
    0.78
    Activations Density 0.219%

    No Known Activations