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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14641
    Prev
    Next
    INDEX
    Explanations

    terms related to incarceration and imprisonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.67
     bordir
    -0.53
    RectangleBorder
    -0.53
    OfDay
    -0.51
     InputDecoration
    -0.47
    LETIN
    -0.47
    WebVitals
    -0.46
    clusal
    -0.45
    EDEFAULT
    -0.44
    Portail
    -0.43
    POSITIVE LOGITS
     prison
    1.23
     Prison
    1.09
    Prison
    0.99
     jail
    0.97
    prison
    0.95
     PRISON
    0.93
     prisons
    0.91
     Prisons
    0.91
     Jail
    0.88
     prisoner
    0.85
    Activations Density 0.294%

    No Known Activations