© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 4944
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "do" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -1.05
     itſelf
    -1.00
     Jefus
    -0.98
     themſelves
    -0.93
     ſche
    -0.92
     himſelf
    -0.90
     pleaſure
    -0.88
     ſever
    -0.88
     myſelf
    -0.87
    ſelf
    -0.85
    POSITIVE LOGITS
     do
    1.23
     done
    1.22
    Do
    1.03
     Do
    1.00
     does
    0.94
     DONE
    0.93
     DOING
    0.89
    Doing
    0.89
    doing
    0.89
     doing
    0.88
    Activations Density 0.051%

    No Known Activations