© 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. 31906
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and question marks

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

    sentence endings

    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
     Rukh
    -0.59
    Tracce
    -0.54
     Wikimédia
    -0.47
    Erstellt
    -0.46
    Kontrola
    -0.45
     mime
    -0.44
     program
    -0.42
    ENTY
    -0.42
     entre
    -0.41
     env
    -0.41
    POSITIVE LOGITS
    これで
    0.75
    still
    0.65
    }))
    0.65
    otherwise
    0.61
     oplossing
    0.60
     fortfarande
    0.59
     Böyle
    0.59
     يتيمه
    0.58
    makeatother
    0.58
     اكتوبر
    0.57
    Activations Density 0.293%

    No Known Activations