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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2086
    Prev
    Next
    INDEX
    Explanations

    concepts related to incarceration and penal sentences

    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
     resourceCulture
    -0.97
     Roskov
    -0.90
    WebElementEntity
    -0.85
    WriteTagHelper
    -0.81
    tahui
    -0.81
    elemField
    -0.81
    ValueStyle
    -0.80
    Và
    -0.79
    contentLoaded
    -0.78
     ویکی‌پدی
    -0.77
    POSITIVE LOGITS
     prison
    3.03
     Prison
    2.86
    Prison
    2.64
     prisons
    2.58
     PRISON
    2.56
    prison
    2.51
     jail
    2.36
     Prisons
    2.31
     prisoners
    2.21
     Prisoners
    2.07
    Activations Density 0.116%

    No Known Activations