© 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. 5770
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to statistical measures and scientific processes

    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
     CreateTagHelper
    -0.67
    RenderAtEndOf
    -0.60
    SourceChecksum
    -0.56
    ngdoc
    -0.55
    UserScript
    -0.54
     ModelExpression
    -0.50
    ۗ
    -0.49
    AndEndTag
    -0.49
     &___
    -0.48
    AnchorStyles
    -0.48
    POSITIVE LOGITS
     Ex
    3.42
     ex
    3.39
    Ex
    3.05
    ex
    2.91
     EX
    2.75
    EX
    2.39
     eks
    2.34
     exc
    1.89
     Eks
    1.80
     эк
    1.74
    Activations Density 1.168%

    No Known Activations