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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15986
    Prev
    Next
    INDEX
    Explanations

    references and discussions about video games

    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
    पया
    -0.42
    oinette
    -0.39
     rense
    -0.38
     proteção
    -0.37
    Gradient
    -0.36
     intervenciones
    -0.36
     näky
    -0.35
    ésultat
    -0.35
     étapes
    -0.34
     asamblea
    -0.34
    POSITIVE LOGITS
     gameplay
    1.14
     developer
    1.13
     devs
    1.13
     developers
    1.10
     game
    1.07
     playable
    1.06
     DLC
    0.98
     games
    0.96
     Developer
    0.89
    developer
    0.88
    Activations Density 0.452%

    No Known Activations