© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 6644
    Prev
    Next
    INDEX
    Explanations

    instances of possession-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.73
     IndexPath
    -0.73
     الرياضيه
    -0.71
    ⓘ
    -0.71
    rafat
    -0.68
    RequestMapping
    -0.68
     Enoch
    -0.68
    typeorm
    -0.68
    煦
    -0.68
    nebago
    -0.66
    POSITIVE LOGITS
     Possession
    0.96
     possessed
    0.93
     Designer
    0.92
    Poss
    0.88
     possession
    0.87
    poss
    0.84
    Designer
    0.84
     possessing
    0.82
     designer
    0.82
     Designers
    0.81
    Activations Density 0.089%

    No Known Activations