© 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
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3158
    Prev
    Next
    INDEX
    Explanations

    commands or instructions involving the act of asking or telling someone to perform actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.59
    uia
    -0.44
     contextLoads
    -0.44
     iprot
    -0.43
    AddTagHelper
    -0.43
    確かに
    -0.43
    Facts
    -0.43
    facts
    -0.41
     Facts
    -0.41
    ifoli
    -0.41
    POSITIVE LOGITS
     doporu
    0.44
     sebaiknya
    0.40
    hould
    0.39
    Keep
    0.38
     hjel
    0.38
     solle
    0.38
    Jangan
    0.37
     should
    0.37
     recomendado
    0.36
     Jangan
    0.36
    Activations Density 0.725%

    No Known Activations