© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10539
    Prev
    Next
    INDEX
    Explanations

    legal terms and phrases related to guilty pleas and court proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Pleading guilty or not guilty

    np_acts-logits-general · gemini-2.0-flash

    pleading guilty or not guilty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.66
    IUrlHelper
    -0.62
     autorytatywna
    -0.59
     للمعارف
    -0.56
    Sucesor
    -0.56
    choenen
    -0.55
    DataMember
    -0.50
     Auvergne
    -0.50
     trå
    -0.49
     Lopes
    -0.49
    POSITIVE LOGITS
     plea
    1.20
     settlement
    1.09
     guilty
    0.99
     pleaded
    0.97
     Plea
    0.94
     settlements
    0.92
     settle
    0.92
     pleas
    0.91
     plead
    0.91
     Ple
    0.88
    Activations Density 0.704%

    No Known Activations