© 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. 33-GEMMASCOPE-RES-16K
    6. 12176
    Prev
    Next
    INDEX
    Explanations

    phrases related to auditing processes and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.74
    enterOuterAlt
    -0.52
    ParallelGroup
    -0.49
    verifyException
    -0.49
    gyar
    -0.48
    titleMargin
    -0.47
     ligiloj
    -0.47
    addPreferredGap
    -0.46
     Мексичка
    -0.46
    цезда
    -0.46
    POSITIVE LOGITS
     tender
    1.55
     tenders
    1.45
     Tender
    1.34
    tender
    1.30
    Tender
    1.30
     bidding
    1.23
     procurement
    1.20
     RFP
    1.17
     bids
    1.09
     Bidding
    1.05
    Activations Density 0.167%

    No Known Activations