© 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. 37-GEMMASCOPE-RES-16K
    11. 3598
    Prev
    Next
    INDEX
    Explanations

    visual artifacts and elements related to modern art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.72
     snippetHide
    -0.51
    liceerd
    -0.50
    AccessorTable
    -0.48
    ViewImports
    -0.47
    XmlAccessorType
    -0.47
    AutoField
    -0.47
    +#+#
    -0.46
    Buildable
    -0.46
    GTCX
    -0.44
    POSITIVE LOGITS
     abstract
    0.72
     Abstract
    0.65
     abstra
    0.63
     cub
    0.61
    abstract
    0.60
     abstraction
    0.60
     Impression
    0.59
    抽象
    0.58
    Abstract
    0.55
     abstracts
    0.53
    Activations Density 0.225%

    No Known Activations