© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10839
    Prev
    Next
    INDEX
    Explanations

    references to the game development and download processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ragalactic
    -0.31
     vigencia
    -0.30
     kirj
    -0.30
    로그램
    -0.30
    ogaster
    -0.30
     vantaggio
    -0.28
    Gradient
    -0.28
     ventajas
    -0.28
     rense
    -0.27
     kolay
    -0.27
    POSITIVE LOGITS
     developer
    1.16
     gameplay
    1.05
     developers
    1.05
     devs
    1.00
     playable
    0.96
     games
    0.94
    developer
    0.93
     game
    0.91
     publisher
    0.90
     Developer
    0.90
    Activations Density 0.267%

    No Known Activations