© 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. 1-GEMMASCOPE-RES-16K
    11. 2218
    Prev
    Next
    INDEX
    Explanations

    references to the first-person pronoun "me" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    diğini
    -0.34
     ditangkap
    -0.34
    miyorum
    -0.34
    diğinde
    -0.34
    TRAILING
    -0.31
    mişti
    -0.31
     Domini
    -0.28
    lüğ
    -0.28
    mort
    -0.28
     Wordsworth
    -0.28
    POSITIVE LOGITS
     ME
    2.00
    ME
    1.95
     Me
    1.91
    Me
    1.91
    me
    1.84
     ме
    1.77
     Mea
    1.70
    ме
    1.70
     Mei
    1.65
    Mea
    1.65
    Activations Density 0.221%

    No Known Activations