© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 7549
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "had" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    今は
    -0.52
     now
    -0.50
     Administrativna
    -0.48
    今も
    -0.47
     huidige
    -0.46
     podendo
    -0.45
     actualidad
    -0.45
    今でも
    -0.44
    featureID
    -0.44
    現在は
    -0.44
    POSITIVE LOGITS
     originally
    1.11
     hoped
    1.10
     previously
    0.96
     ursprünglich
    0.91
     auparavant
    0.86
     earlier
    0.85
     originalmente
    0.85
    originally
    0.84
     zuvor
    0.84
    Originally
    0.82
    Activations Density 0.139%

    No Known Activations