© 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. 0-GEMMASCOPE-RES-16K
    11. 7619
    Prev
    Next
    INDEX
    Explanations

    terms and words related to glucose and glycan structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.58
     Châ
    -0.51
    Бележки
    -0.49
    Serviço
    -0.48
    intios
    -0.47
    iseite
    -0.45
     وتسجيلات
    -0.44
     Gauthier
    -0.44
     désolés
    -0.44
     ***!
    -0.44
    POSITIVE LOGITS
     Gla
    1.37
    Gla
    1.31
     gl
    1.30
     gla
    1.28
     Glu
    1.26
    gla
    1.25
     Gl
    1.20
     GL
    1.17
    Gl
    1.16
     glu
    1.15
    Activations Density 1.500%

    No Known Activations