© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-131K
    11. 76161
    Prev
    Next
    INDEX
    Explanations

    references to personal ownership or possession

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

    my story, expression, favorite

    np_acts-logits-general · gemini-2.5-flash-lite

    It detects occurrences of the capitalized word "My", especially when used at the start of a turn or sentence.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     bezeichneter
    -0.43
     pungkasnya
    -0.40
    adaptiveStyles
    -0.39
     overras
    -0.35
    outWeight
    -0.35
    titleMargin
    -0.34
    PMailer
    -0.33
    Autoritní
    -0.33
     šķ
    -0.33
    AccessorTable
    -0.33
    POSITIVE LOGITS
     queſto
    0.66
     好文分享
    0.61
    EnglishChoose
    0.60
     ſeines
    0.60
     imagui
    0.59
     dieſen
    0.59
     ſuo
    0.58
     vooz
    0.57
     ſeinen
    0.57
     $_-
    0.56
    Activations Density 0.011%

    No Known Activations