© 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-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 31642
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of a document or section

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

    placeholder names and numbers followed by diverse subsequent tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    AndEndTag
    -1.28
     насељу
    -1.13
     CreateTagHelper
    -1.02
    NUMX
    -0.98
     Мексичка
    -0.95
     незавершена
    -0.93
    awtextra
    -0.91
    Jeografia
    -0.91
    principalColumn
    -0.88
    Havolalar
    -0.85
    POSITIVE LOGITS
    â
    0.48
    !
    0.48
     years
    0.46
    ...
    0.45
    this
    0.45
     individu
    0.44
    伺
    0.44
    years
    0.43
    mspace
    0.42
    ................
    0.42
    Activations Density 0.009%

    No Known Activations