© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 96041
    Prev
    Next
    INDEX
    Explanations

    variations of the word "My" and its possessive forms

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

    my followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.62
    complexContent
    -0.52
    IsContent
    -0.52
    blurRadius
    -0.46
     leſs
    -0.45
     hinweg
    -0.45
    ImageContext
    -0.45
     itſelf
    -0.44
    enumi
    -0.44
    ंदीखरीदारी
    -0.44
    POSITIVE LOGITS
     My
    1.56
    My
    1.45
     MY
    1.20
     my
    1.11
    MY
    1.07
    getMy
    1.06
    my
    1.02
    Моя
    0.93
     Мой
    0.85
     Meine
    0.82
    Activations Density 0.007%

    No Known Activations