© 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. 9559
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "perfect" in various contexts

    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
    -0.57
     Kebijakan
    -0.52
     argint
    -0.51
     flotante
    -0.51
     moviliz
    -0.51
     Senhora
    -0.50
    colgante
    -0.50
     cuerdas
    -0.50
     fantasmas
    -0.49
     libremente
    -0.48
    POSITIVE LOGITS
     perfect
    2.36
     Perfect
    2.25
    Perfect
    2.22
    perfect
    2.20
     perfection
    2.03
     PERFECT
    2.02
    PERFECT
    1.88
     Perfection
    1.77
     perfe
    1.64
    Perfection
    1.64
    Activations Density 0.304%

    No Known Activations