© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 6266
    Prev
    Next
    INDEX
    Explanations

    instances of the word "valuable" and concepts related to important resources or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.66
    sizeCache
    -0.65
    ंदीखरीदारी
    -0.58
     насељу
    -0.56
     للمعارف
    -0.56
     دیکھیے
    -0.55
     مرئيه
    -0.55
    WebElementEntity
    -0.54
    GEBURTSDATUM
    -0.54
    SizeMode
    -0.52
    POSITIVE LOGITS
     precious
    1.16
     précieux
    1.04
     valuable
    1.00
    precious
    0.90
     Valuable
    0.89
     Precious
    0.87
     précie
    0.87
    Precious
    0.82
    valuable
    0.80
     important
    0.80
    Activations Density 0.373%

    No Known Activations