© 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. 3-GEMMASCOPE-RES-16K
    11. 1125
    Prev
    Next
    INDEX
    Explanations

    references to innocence and the protection of innocent individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Mathias
    -0.72
    ilangkan
    -0.65
     وتسجيلات
    -0.61
    shifted
    -0.60
    agot
    -0.60
     visst
    -0.59
     Pelham
    -0.59
    impresa
    -0.57
    arım
    -0.57
     Suivez
    -0.57
    POSITIVE LOGITS
     innocent
    1.93
    Innoc
    1.77
     Innocent
    1.77
    innocent
    1.70
     innocence
    1.64
    innoc
    1.58
     innoc
    1.52
     Innocence
    1.48
     inocente
    1.35
     Innoc
    1.33
    Activations Density 0.175%

    No Known Activations