© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12043
    Prev
    Next
    INDEX
    Explanations

    elements related to prison settings and inmate arrangements

    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
     auquel
    -0.35
     intereses
    -0.34
    arrol
    -0.34
     sufri
    -0.33
    erschein
    -0.33
    atteindre
    -0.33
     parvenir
    -0.33
     emplear
    -0.32
    ียว
    -0.32
    chèque
    -0.32
    POSITIVE LOGITS
     rooms
    0.82
     downstairs
    0.79
     room
    0.76
     upstairs
    0.69
     Rooms
    0.66
     Room
    0.63
     esternos
    0.62
    RegressionTest
    0.61
    Rooms
    0.60
    webElementXpaths
    0.60
    Activations Density 0.173%

    No Known Activations