© 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. 10071
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal reflection and life experiences

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

    my life, your life, his life

    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
     life
    -1.45
     Life
    -1.21
    life
    -1.19
     LIFE
    -1.16
    Life
    -1.13
    LIFE
    -1.05
     lifetime
    -0.98
     vida
    -0.97
     Leben
    -0.91
     жизнь
    -0.90
    POSITIVE LOGITS
    Rest
    0.40
    rest
    0.39
     rest
    0.38
     Italijanski
    0.35
     Rest
    0.34
     Wikimedijinoj
    0.32
     restant
    0.31
     Mantle
    0.31
    دانشنامهٔ
    0.31
    innung
    0.31
    Activations Density 0.020%

    No Known Activations