© 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. 9-GEMMASCOPE-RES-131K
    11. 107064
    Prev
    Next
    INDEX
    Explanations

    references to pens and their usage

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

    pen, pencil

    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
     Arche
    -0.47
    いしい
    -0.46
     archeological
    -0.45
    Maße
    -0.44
    archae
    -0.42
     Concession
    -0.40
     görüntüleri
    -0.40
     archaeological
    -0.40
     arche
    -0.40
     Wallis
    -0.40
    POSITIVE LOGITS
     pencil
    1.09
     pen
    1.03
     pencils
    1.02
     lápiz
    1.00
     pens
    1.00
    Pencil
    0.98
     caneta
    0.97
     Pencil
    0.95
     lápis
    0.94
    pencil
    0.88
    Activations Density 0.017%

    No Known Activations