© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 98682
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or ownership

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

    possess / own / have

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     themſelves
    -0.44
    NextPage
    -0.40
     Houſe
    -0.40
     étapes
    -0.39
     steps
    -0.39
     chantier
    -0.39
    Steps
    -0.39
    Grüsse
    -0.38
     pasos
    -0.38
    later
    -0.38
    POSITIVE LOGITS
     posiada
    0.90
     possesses
    0.89
     memiliki
    0.87
     possess
    0.85
     possessed
    0.82
     besitzt
    0.81
    拥有
    0.81
     posee
    0.79
     mempunyai
    0.78
     possessing
    0.77
    Activations Density 0.031%

    No Known Activations