© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 884
    Prev
    Next
    INDEX
    Explanations

    expressions of remorse or the concept of apology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SUCCESS
    -0.23
     contract
    -0.23
     Lagi
    -0.23
     RESIST
    -0.23
     administ
    -0.22
     resistant
    -0.22
     benef
    -0.21
     prak
    -0.21
     nä
    -0.21
     zau
    -0.21
    POSITIVE LOGITS
     apologies
    2.67
     apology
    2.66
     apologize
    2.64
     sorry
    2.58
     apologise
    2.48
     apologized
    2.47
     apologizing
    2.42
     Sorry
    2.36
     SORRY
    2.31
     apologised
    2.30
    Activations Density 0.380%

    No Known Activations