© 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. 1-GEMMASCOPE-RES-16K
    11. 8470
    Prev
    Next
    INDEX
    Explanations

    terms related to incarceration and prison systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.88
     referenties
    -0.77
     Chwiliwch
    -0.75
    WebVitals
    -0.73
    webElementGuid
    -0.70
    الإنجليزية
    -0.70
     resourceCulture
    -0.69
     Administrativna
    -0.67
     ModelExpression
    -0.67
     متعلقه
    -0.63
    POSITIVE LOGITS
     prison
    1.83
     prisoners
    1.80
    Prison
    1.78
     Prison
    1.75
    prison
    1.73
     prisoner
    1.68
     PRISON
    1.60
     prisons
    1.56
     Prisoners
    1.53
     Prisons
    1.41
    Activations Density 0.040%

    No Known Activations