© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 15643
    Prev
    Next
    INDEX
    Explanations

    instances of the word "undertaken" and its variants, indicating it searches for discussions about research, studies, or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    undertaken projects and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.56
     Keuangan
    -0.54
    gehalt
    -0.53
     ainfi
    -0.50
    phemy
    -0.50
     Privacidade
    -0.50
    icitis
    -0.49
    Groetjes
    -0.49
     keuangan
    -0.48
     supaya
    -0.48
    POSITIVE LOGITS
     undertaken
    1.66
     undertake
    1.53
     undertook
    1.46
     undertaking
    1.43
     undertakes
    1.30
     undertakings
    1.05
     undergone
    0.75
     underway
    0.74
     conducted
    0.71
     underta
    0.70
    Activations Density 0.004%

    No Known Activations