© 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. 18-GEMMASCOPE-RES-16K
    11. 4482
    Prev
    Next
    INDEX
    Explanations

    expressions of apology and expressions of regret

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

    Expressing apology or regret

    np_acts-logits-general · gemini-2.0-flash

    apologize sorry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    statusText
    -0.56
    čnega
    -0.49
    楽しみです
    -0.48
    Stateless
    -0.47
    didSet
    -0.46
    ]").
    -0.44
    Fav
    -0.43
    ]")]
    -0.42
     Tiro
    -0.42
    čnih
    -0.42
    POSITIVE LOGITS
     sorry
    2.48
     Sorry
    2.19
    sorry
    2.14
     apologies
    2.13
     apologize
    2.08
    Sorry
    2.04
     SORRY
    2.01
     apology
    1.97
     apologized
    1.84
     apologise
    1.83
    Activations Density 0.200%

    No Known Activations