© 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. 3703
    Prev
    Next
    INDEX
    Explanations

    discussions regarding economic systems and their impact on labor

    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
     kaarangay
    -0.63
    SourceChecksum
    -0.57
     CreateTagHelper
    -0.57
     ProtoMessage
    -0.57
    FormTagHelper
    -0.56
    帖最后由
    -0.53
    fromnode
    -0.52
    enderror
    -0.52
    Werdegang
    -0.51
     propOrder
    -0.49
    POSITIVE LOGITS
     much
    2.34
    Much
    2.09
    much
    2.08
     Much
    1.96
     MUCH
    1.95
     far
    1.84
     mucho
    1.70
     jauh
    1.68
     гораздо
    1.64
     намного
    1.64
    Activations Density 0.743%

    No Known Activations