© 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. 6348
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and geographical locations

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

    Armenia and Armenian

    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
    tagHelperRunner
    -0.43
    脚注の使い方
    -0.37
    EndGlobalSection
    -0.33
     semacam
    -0.33
     faudra
    -0.31
     Trennung
    -0.31
    ſelf
    -0.31
     Præ
    -0.29
     sappi
    -0.29
     Ankunft
    -0.29
    POSITIVE LOGITS
     Armenian
    1.21
     Armenia
    1.09
     Yerevan
    1.05
    Armen
    1.02
    Armenia
    1.00
     armen
    0.98
     Armenians
    0.94
     Armen
    0.91
     Арме
    0.78
    armen
    0.77
    Activations Density 0.015%

    No Known Activations