© 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. 2-GEMMASCOPE-RES-16K
    11. 4187
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "had."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Torrey
    -0.91
     occafion
    -0.89
     perſon
    -0.88
     Roskov
    -0.87
     myſelf
    -0.85
     Reuter
    -0.85
     Pergamon
    -0.80
    <caption>
    -0.80
     Ressource
    -0.80
    woordig
    -0.80
    POSITIVE LOGITS
     had
    2.76
     Had
    2.58
    Had
    2.54
    had
    2.47
     HAD
    2.28
    HAD
    1.76
     hatte
    1.52
     είχε
    1.51
     avaient
    1.47
     hadden
    1.47
    Activations Density 0.111%

    No Known Activations