© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10352
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to 'me' or self-reference

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

    "Me" followed by a variety of words

    np_acts-logits-general · gemini-2.0-flash

    Me followed by other words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FontOfSize
    -0.72
    хьтан
    -0.72
    ')")
    -0.68
    ]--;
    -0.68
    WireFormatLite
    -0.66
    jalá
    -0.61
    PHeader
    -0.60
     typelib
    -0.59
     aix
    -0.58
    webElementXpaths
    -0.58
    POSITIVE LOGITS
    Me
    0.86
     ме
    0.80
     Me
    0.79
     Mehta
    0.70
     MET
    0.68
     Ме
    0.68
    ME
    0.67
    tvguidetime
    0.67
     Meier
    0.67
     ME
    0.65
    Activations Density 0.154%

    No Known Activations