© 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. 8262
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "do" in various forms and 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
    pecabe
    -0.82
     Meksika
    -0.78
     desmotivaciones
    -0.77
     незавершена
    -0.75
     pinulongan
    -0.70
    berdayakan
    -0.69
    Atentamente
    -0.69
    verifyException
    -0.69
    bootstrapcdn
    -0.69
     myſelf
    -0.68
    POSITIVE LOGITS
     do
    2.72
     did
    1.88
     doing
    1.74
     does
    1.69
     done
    1.49
    do
    1.42
     Doing
    1.33
    Doing
    1.29
    did
    1.27
    doing
    1.27
    Activations Density 0.202%

    No Known Activations