© 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. 1398
    Prev
    Next
    INDEX
    Explanations

    references to religious identities and their influence on personal characteristics or behaviors

    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
    孩子们
    -0.55
    皆さん
    -0.46
    同学们
    -0.46
     çocuklar
    -0.46
    人们
    -0.46
     eds
    -0.46
     quienes
    -0.44
    人們
    -0.44
     smlou
    -0.43
     kvinder
    -0.43
    POSITIVE LOGITS
     performer
    1.48
     person
    1.44
     researcher
    1.43
     musician
    1.38
     practitioner
    1.37
     athlete
    1.36
     participant
    1.34
     golfer
    1.34
     player
    1.33
     worker
    1.32
    Activations Density 3.312%

    No Known Activations