© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 21628
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in legal or citizenship contexts

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

    Vietnamese names like Nguyen and others

    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
     <>",
    -0.61
    يميديا
    -0.60
    Vidite
    -0.60
    SequentialGroup
    -0.52
    AntiForgeryToken
    -0.52
     createState
    -0.51
    enderror
    -0.50
    +#+#
    -0.50
     HasFactory
    -0.49
    getDeclared
    -0.47
    POSITIVE LOGITS
    immig
    0.82
     immig
    0.82
     immigrant
    0.81
     immigrants
    0.80
     emigrated
    0.72
     Immigrants
    0.68
     Immigrant
    0.66
     inmig
    0.65
     refugee
    0.63
     immigration
    0.60
    Activations Density 0.093%

    No Known Activations