© 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. 40-GEMMASCOPE-RES-16K
    6. 5199
    Prev
    Next
    INDEX
    Explanations

    terms related to legal status and professional roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.58
     createState
    -0.50
    haikusbot
    -0.47
    CloseOperation
    -0.47
    Obrázky
    -0.45
    chartInstance
    -0.44
    +#+#
    -0.43
     StatelessWidget
    -0.41
    detectChanges
    -0.40
    styleUrls
    -0.40
    POSITIVE LOGITS
     lawyers
    2.53
     lawyer
    2.45
     attorneys
    2.41
     Lawyers
    2.30
     attorney
    2.28
     legal
    2.25
     Lawyer
    2.23
     Legal
    2.23
    Legal
    2.16
    lawyer
    2.11
    Activations Density 1.574%

    No Known Activations