© 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. 13154
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duality or the concept of "both."

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

    both X and Y

    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
     quelconque
    -0.52
     båda
    -0.51
     dokonce
    -0.51
     навіть
    -0.49
     beiden
    -0.48
     thậm
    -0.48
     nawet
    -0.47
     forskjellige
    -0.47
     даже
    -0.47
     sebagainya
    -0.47
    POSITIVE LOGITS
     physically
    0.62
     figur
    0.61
     censiti
    0.56
     Мексичка
    0.54
     monet
    0.53
     carrot
    0.52
     للمعارف
    0.52
    ɯ
    0.51
    FormTagHelper
    0.50
     visually
    0.49
    Activations Density 0.034%

    No Known Activations