© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 10652
    Prev
    Next
    INDEX
    Explanations

    references to biological processes and measurements related to health and medicine

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    DSi consumption

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.69
    <sup>
    -0.64
     such
    -0.61
     whatever
    -0.59
     (
    -0.57
    autoIncrement
    -0.56
     qualcosa
    -0.56
     fonctionner
    -0.55
     herhangi
    -0.53
     irgend
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.92
    : 
    0.74
     betweenstory
    0.71
     :
    0.70
    Tikang
    0.69
    rungsseite
    0.67
    '".
    0.66
    ReusableCell
    0.65
     initComponents
    0.64
     AppModule
    0.64
    Activations Density 0.688%

    No Known Activations