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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 5764
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "apologize" and related concepts of remorse and regret

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

    the word "apologize" and related forms like "apology" and "apologizing".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.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
     benef
    -0.30
     контра
    -0.29
     Gra
    -0.27
     консер
    -0.26
     consi
    -0.25
     Lagi
    -0.24
     gradi
    -0.24
     وارد
    -0.23
     бю
    -0.23
     administ
    -0.23
    POSITIVE LOGITS
     apology
    2.80
     apologies
    2.78
     apologize
    2.78
     apologise
    2.64
     apologized
    2.64
     apologizing
    2.55
     apologised
    2.45
     sorry
    2.38
     apolog
    2.36
     apologe
    2.20
    Activations Density 0.422%

    No Known Activations