© 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. 31896
    Prev
    Next
    INDEX
    Explanations

    date and time formatting patterns

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

    date day month name

    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
    íncia
    -0.44
     gebunden
    -0.40
    <eos>
    -0.40
    Restrictions
    -0.39
    Spoiler
    -0.39
     restricted
    -0.39
     teljes
    -0.38
     complètes
    -0.37
     betra
    -0.36
    frust
    -0.36
    POSITIVE LOGITS
     يتيمه
    0.88
     الحره
    0.86
    OfWork
    0.76
    SequentialGroup
    0.74
    Diwedd
    0.73
    AnchorStyles
    0.71
    afficheront
    0.70
    󠁴
    0.69
     gainera
    0.69
     InputDecoration
    0.69
    Activations Density 0.035%

    No Known Activations