Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7400
    Prev
    Next
    INDEX
    Explanations

    references to incarceration and the criminal justice system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    FromNib
    -0.40
    üyada
    -0.37
     يتيمه
    -0.37
    RunAsync
    -0.35
    Aiheesta
    -0.35
     Royal
    -0.35
     Münch
    -0.34
     Gorb
    -0.34
     سما
    -0.34
     Schon
    -0.33
    POSITIVE LOGITS
     incarceration
    0.58
     criminal
    0.58
     jails
    0.54
     Normdatei
    0.53
     incarcerated
    0.52
     prison
    0.52
    Criminal
    0.50
     Ceinture
    0.50
     jail
    0.49
     prisoners
    0.49
    Activations Density 0.082%

    No Known Activations