© 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-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7944
    Prev
    Next
    INDEX
    Explanations

    instances of apologies and expressions of remorse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageContext
    -0.65
    SequentialGroup
    -0.61
    IsMutable
    -0.60
     createSlice
    -0.60
     Monfieur
    -0.60
     ſind
    -0.59
     poffe
    -0.59
    IntoConstraints
    -0.59
    BeginContext
    -0.57
     $_"
    -0.57
    POSITIVE LOGITS
     apology
    0.84
     apologized
    0.76
     apologize
    0.75
     apologizing
    0.74
     apologised
    0.73
     apologise
    0.69
     apologies
    0.68
     SORRY
    0.64
    道歉
    0.63
     remorse
    0.60
    Activations Density 0.165%

    No Known Activations