© 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. 5-GEMMASCOPE-RES-16K
    11. 6093
    Prev
    Next
    INDEX
    Explanations

    sections of the text that contain formatting or visual separators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riwal
    -0.72
     Keyes
    -0.69
    userRepository
    -0.68
    djangoproject
    -0.67
     Pollack
    -0.65
     smtplib
    -0.63
    istration
    -0.62
    版
    -0.62
     Selig
    -0.62
    RegressionTest
    -0.61
    POSITIVE LOGITS
    ................
    1.95
    ...............
    1.33
    ..............
    1.27
    .........
    1.21
    ........
    1.17
    .............
    1.17
    ............
    1.16
    ...........
    1.13
    ..........
    1.11
     ...............
    1.06
    Activations Density 0.180%

    No Known Activations