© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 42228
    Prev
    Next
    INDEX
    Explanations

    references to judicial decisions and legal terminology

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

    official pronouncements followed by "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.74
     protoimpl
    -0.58
    complexContent
    -0.57
     Украи
    -0.55
    expandindo
    -0.54
     DbType
    -0.53
     Украї
    -0.51
     StatelessWidget
    -0.49
     propOrder
    -0.48
     للمعارف
    -0.48
    POSITIVE LOGITS
     của
    1.09
    ของ
    1.05
     of
    1.02
     milik
    0.90
     ofthe
    0.75
     של
    0.70
     της
    0.67
    ofthe
    0.65
     belonging
    0.65
     ของ
    0.59
    Activations Density 0.225%

    No Known Activations