© 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. 11-GEMMASCOPE-RES-16K
    11. 5115
    Prev
    Next
    INDEX
    Explanations

    expressions of apology or regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Werde
    -0.32
     cupboards
    -0.31
    listdir
    -0.31
    sweise
    -0.31
    XtraBars
    -0.31
    からです
    -0.31
    果
    -0.31
     Initiatives
    -0.31
     prefeitura
    -0.31
     villaggio
    -0.31
    POSITIVE LOGITS
     sorry
    1.30
    sorry
    1.25
     SORRY
    1.22
     Sorry
    1.21
    Sorry
    1.20
     apologize
    1.01
     apologies
    0.95
     apologise
    0.95
     apologized
    0.94
     apology
    0.93
    Activations Density 0.119%

    No Known Activations