© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 13813
    Prev
    Next
    INDEX
    Explanations

    references to academic appointments and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    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
    -0.59
    peers
    -0.52
    同学们
    -0.50
    getUsers
    -0.49
    wives
    -0.46
     getUsers
    -0.46
     eds
    -0.46
     Dealers
    -0.43
    clientes
    -0.43
     wives
    -0.42
    POSITIVE LOGITS
     person
    1.70
     woman
    1.43
     guy
    1.37
     athlete
    1.29
     musician
    1.23
     pessoa
    1.23
     businessman
    1.21
     golfer
    1.20
     player
    1.17
     teenager
    1.17
    Activations Density 1.784%

    No Known Activations