© 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. 2-GEMMASCOPE-RES-16K
    11. 12423
    Prev
    Next
    INDEX
    Explanations

    instances of apologies or expressions of regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.54
    Portail
    -0.52
    canestro
    -0.49
     Reception
    -0.45
    WebVitals
    -0.44
     vVar
    -0.44
    $_['
    -0.42
    前期
    -0.42
    Искәрмәләр
    -0.41
     Vlas
    -0.41
    POSITIVE LOGITS
     apologize
    1.59
     apology
    1.51
     apologies
    1.50
     apologise
    1.48
     apologized
    1.42
     apologised
    1.39
     apologizing
    1.33
     Apo
    1.30
    Apologies
    1.25
     apolog
    1.24
    Activations Density 0.356%

    No Known Activations