© 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. 36-GEMMASCOPE-RES-16K
    11. 9065
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and game mechanics, specifically interactions and conditions involving creatures and their states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.38
     dagelijks
    -0.34
     genealog
    -0.32
     års
    -0.32
     år
    -0.32
     Epis
    -0.31
     gewel
    -0.31
     grano
    -0.31
     tournée
    -0.30
     gräns
    -0.30
    POSITIVE LOGITS
     aggro
    0.90
     respawn
    0.86
     spawn
    0.77
     spawns
    0.77
     melee
    0.76
     teleport
    0.75
     spamming
    0.75
     ambush
    0.73
     cowardly
    0.73
     attacking
    0.72
    Activations Density 0.251%

    No Known Activations