© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9455
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns, particularly variations and occurrences of "I" or "i."

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

    Token "I" or "i" at the beginning of a sentence

    np_acts-logits-general · gemini-2.0-flash

    i followed by statement or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SDLK
    -0.70
     BERNAMA
    -0.58
    adaptiveStyles
    -0.58
    anee
    -0.57
    flink
    -0.54
     againſt
    -0.54
    ofday
    -0.53
     Efq
    -0.52
     himſelf
    -0.50
    RectangleBorder
    -0.50
    POSITIVE LOGITS
     am
    0.72
     Am
    0.66
     don
    0.62
     think
    0.57
     guess
    0.53
     hate
    0.52
     wish
    0.51
     AM
    0.51
     forgot
    0.51
     agree
    0.50
    Activations Density 0.184%

    No Known Activations