© 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. 2-GEMMASCOPE-RES-16K
    11. 1003
    Prev
    Next
    INDEX
    Explanations

    statements related to licensing and file headers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     peran
    -0.59
    ceb
    -0.56
    meral
    -0.54
    Luka
    -0.54
     ActionResult
    -0.54
    icle
    -0.52
    veer
    -0.52
     vetro
    -0.52
     Cliffs
    -0.50
     DEAD
    -0.50
    POSITIVE LOGITS
    ");
    2.14
    ");
    1.92
    "));
    1.79
    "))
    1.78
    ")
    1.78
    "),
    1.76
    ").
    1.70
    ")[
    1.70
    ")).
    1.66
    ")
    1.65
    Activations Density 0.106%

    No Known Activations