© 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. 17-GEMMASCOPE-RES-16K
    11. 604
    Prev
    Next
    INDEX
    Explanations

    expressions of remorse and apologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.62
    clusal
    -0.58
     Italijanski
    -0.55
    urator
    -0.54
    рядок
    -0.54
     userSchema
    -0.54
    arean
    -0.53
     nourished
    -0.52
     conserve
    -0.52
    zzleHttp
    -0.51
    POSITIVE LOGITS
     apologized
    1.33
     apologizing
    1.32
     apology
    1.31
     apologize
    1.22
     apologised
    1.19
     apologies
    1.16
     remorse
    1.11
     apologise
    1.10
     apologe
    1.09
     apolog
    1.03
    Activations Density 0.250%

    No Known Activations