© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 110454
    Prev
    Next
    INDEX
    Explanations

    instances of apologies or expressions of remorse in a social context

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

    he and his

    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
     оно
    -0.56
     Оно
    -0.55
     zostało
    -0.54
     которое
    -0.54
     juntas
    -0.52
     själva
    -0.52
    它们的
    -0.50
     yourselves
    -0.47
     करती
    -0.47
     deres
    -0.46
    POSITIVE LOGITS
     himself
    2.59
     his
    2.44
    himself
    2.25
    his
    1.92
     himſelf
    1.77
    彼の
    1.74
    彼は
    1.70
    他的
    1.65
     그의
    1.63
     hänen
    1.57
    Activations Density 2.701%

    No Known Activations