© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13305
    Prev
    Next
    INDEX
    Explanations

    expressions of remorse and requests for forgiveness

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

    Expressions of apology and regret

    np_acts-logits-general · gemini-2.0-flash

    apologizing and remorse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onlook
    -0.53
     iVar
    -0.53
     jealous
    -0.52
     "','
    -0.52
     envy
    -0.51
    Datuak
    -0.51
     riv
    -0.51
     mola
    -0.51
     empowerment
    -0.50
    chenkt
    -0.50
    POSITIVE LOGITS
     apologized
    1.10
     apology
    1.08
     remorse
    1.05
     apologizing
    1.03
     apologize
    0.98
     apologised
    0.94
     apologies
    0.89
     apologe
    0.83
     apologise
    0.83
     apolog
    0.78
    Activations Density 0.328%

    No Known Activations