© 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. 9-GEMMASCOPE-RES-131K
    11. 16373
    Prev
    Next
    INDEX
    Explanations

    instances of apologies or expressions of regret

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

    apologize for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.40
    vedra
    -0.38
     manna
    -0.35
     Manit
    -0.34
     Madura
    -0.34
    ắn
    -0.34
     Silla
    -0.33
    RunWith
    -0.33
     Heisenberg
    -0.33
     cassava
    -0.33
    POSITIVE LOGITS
     apologize
    1.89
     apologized
    1.75
     apology
    1.73
     apologise
    1.73
     apologizing
    1.66
     apologised
    1.59
     apologies
    1.57
     apolog
    1.34
     Apo
    1.25
     apologe
    1.20
    Activations Density 0.004%

    No Known Activations