© 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 EvalsExportsinterp-engineNEWAPI 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. 552
    Prev
    Next
    INDEX
    Explanations

    references to oneself or the pronoun "me."

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

    Capitalized "Me" in dialogue or formal contexts

    np_acts-logits-general · gemini-2.0-flash

    words starting with me

    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
    vitis
    -0.57
    enumi
    -0.52
    руд
    -0.51
    Manfaat
    -0.50
    NewGuid
    -0.48
    CRR
    -0.46
    CodeAttribute
    -0.46
     hauteur
    -0.46
     Dadurch
    -0.45
    FontOfSize
    -0.45
    POSITIVE LOGITS
    Me
    0.60
     OFDb
    0.58
    gap
    0.58
     Me
    0.55
    mybatisplus
    0.55
    ########.
    0.54
    KURZBESCHREIBUNG
    0.52
     selves
    0.51
    CFS
    0.50
     Myself
    0.49
    Activations Density 0.098%

    No Known Activations