© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5399
    Prev
    Next
    INDEX
    Explanations

    personal affirmations and expressions of self-identity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    I statements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     wikipagina
    -0.56
     Envelope
    -0.54
    期刊论文
    -0.53
     展板
    -0.52
    Tikang
    -0.52
    geable
    -0.52
    CloseOperation
    -0.51
     برانيه
    -0.51
    EndInit
    -0.51
    orianCalendar
    -0.49
    POSITIVE LOGITS
     Roskov
    0.45
     estekak
    0.36
    новниш
    0.35
    katapos
    0.32
    Ҭ
    0.31
    complexContent
    0.31
     others
    0.30
    angliski
    0.29
    Kaynakça
    0.29
    )}{
    0.29
    Activations Density 0.054%

    No Known Activations