© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 14917
    Prev
    Next
    INDEX
    Explanations

    text related to data formatting and processing

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Jeff
    -0.76
    JEFF
    -0.73
     Thom
    -0.69
    Jeff
    -0.68
     Carson
    -0.68
     Ku
    -0.67
     Carol
    -0.67
     Cowell
    -0.66
     jeff
    -0.66
     Marinette
    -0.65
    POSITIVE LOGITS
     Egan
    0.83
     Nadia
    0.75
     Hanna
    0.73
     Rufus
    0.73
     Bade
    0.71
     McLean
    0.71
     Vaz
    0.70
     Kearns
    0.68
    Nadia
    0.68
     Sven
    0.68
    Activations Density 1.065%

    No Known Activations