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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 4621
    Prev
    Next
    INDEX
    Explanations

    expressions of apology and requests for forgiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    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
    -0.57
    /*
    -0.51
    σμο
    -0.49
    cestershire
    -0.48
     whim
    -0.46
    arean
    -0.45
    geslacht
    -0.44
    demic
    -0.44
    νει
    -0.44
    hless
    -0.43
    POSITIVE LOGITS
     apology
    2.59
     apologize
    2.49
     apologies
    2.43
     apologized
    2.42
     apologizing
    2.32
     apologise
    2.23
     apologised
    2.19
     apolog
    2.05
     sorry
    2.03
     apologe
    1.88
    Activations Density 0.287%

    No Known Activations