© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 3140
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or pursuing something

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

    seek and what is sought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     packageName
    -0.66
     deleteById
    -0.65
     newName
    -0.63
     Robot
    -0.60
     currentPage
    -0.60
    Autowired
    -0.60
     Gm
    -0.58
     randomNumber
    -0.58
     errorMsg
    -0.58
     DPD
    -0.57
    POSITIVE LOGITS
     seek
    1.01
     Seek
    0.93
     seeking
    0.91
     SEEK
    0.90
    seek
    0.87
     sought
    0.86
     seeks
    0.84
    Seek
    0.84
    Seeking
    0.83
    seeking
    0.82
    Activations Density 0.011%

    No Known Activations