© 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. 52792
    Prev
    Next
    INDEX
    Explanations

    instances of the word "narrow" and related variations

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

    narrow followed by a noun

    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
    หวัด
    -0.56
     isof
    -0.56
    ActionEvent
    -0.56
     bookId
    -0.55
     Lect
    -0.52
     SqlCommand
    -0.52
    \{\\
    -0.51
     JBL
    -0.51
    Crist
    -0.51
     getType
    -0.51
    POSITIVE LOGITS
     narrow
    2.11
     Narrow
    1.98
    narrow
    1.96
    Narrow
    1.96
     narrower
    1.48
     narrows
    1.39
     narrowing
    1.35
     narrowed
    1.30
     narrowly
    1.21
    窄
    1.14
    Activations Density 0.005%

    No Known Activations