© 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. 0-GEMMASCOPE-RES-16K
    11. 7612
    Prev
    Next
    INDEX
    Explanations

    references to the term "ace" in various contexts, particularly in formal or organizational settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     desmotivaciones
    -0.89
    Билгалдахарш
    -0.87
     Савезне
    -0.83
     PeEnEo
    -0.81
     Grüsse
    -0.77
    WithIOException
    -0.76
    majánló
    -0.76
     myſelf
    -0.75
     increí
    -0.75
    featureID
    -0.75
    POSITIVE LOGITS
     ace
    0.77
    ace
    0.72
     formal
    0.71
     Ace
    0.66
     mass
    0.60
     Bennett
    0.59
     master
    0.56
     great
    0.54
     perfect
    0.53
     self
    0.52
    Activations Density 0.182%

    No Known Activations