© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10387
    Prev
    Next
    INDEX
    Explanations

    terms related to disciplinary actions and legal proceedings

    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
    
    -0.75
     betweenstory
    -0.64
    TagMode
    -0.57
     oprot
    -0.55
     فريبيس
    -0.54
    awtextra
    -0.52
    MENAFN
    -0.52
     estekak
    -0.52
    featureID
    -0.51
    AddTagHelper
    -0.50
    POSITIVE LOGITS
     disciplinary
    1.60
     discipline
    1.36
     Discipl
    1.31
     suspension
    1.30
    Discipl
    1.26
     Discipline
    1.24
     suspensions
    1.21
     disiplin
    1.21
     discipl
    1.16
    Discipline
    1.15
    Activations Density 0.864%

    No Known Activations