© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 16367
    Prev
    Next
    INDEX
    Explanations

    sections related to acknowledgments and conclusions in academic writing

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ."),
    -0.97
    '],
    
    -0.93
    '])->
    -0.85
    .",
    
    -0.84
    !',
    -0.79
    "],
    
    -0.79
    !",
    -0.79
    */;
    -0.77
    ()],
    -0.76
    ?',
    -0.76
    POSITIVE LOGITS
    :✨
    0.73
     &
    0.66
     summary
    0.62
    Edit
    0.62
     \&
    0.61
     contd
    0.59
     générales
    0.57
    Etc
    0.57
     generales
    0.55
     continued
    0.55
    Activations Density 0.602%

    No Known Activations