Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8265
    Prev
    Next
    INDEX
    Explanations

    medical terminology and references to experimental conditions

    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
     sèche
    -0.44
     armé
    -0.40
     desierto
    -0.39
     profeta
    -0.38
     asesino
    -0.38
     salvaje
    -0.38
     aislado
    -0.37
     trouw
    -0.35
     précé
    -0.34
     jár
    -0.34
    POSITIVE LOGITS
    новништво
    0.61
    出版年
    0.60
    TokenNameLBRACE
    0.57
    ViewFeatures
    0.57
    transQ
    0.53
    MessageTagHelper
    0.52
    elemField
    0.51
     EconPapers
    0.50
     kasarigan
    0.49
     snippetHide
    0.48
    Activations Density 0.678%

    No Known Activations