© 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. 33-GEMMASCOPE-RES-16K
    11. 7872
    Prev
    Next
    INDEX
    Explanations

    specific gameplay elements or mechanics in video games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.54
     GenerationType
    -0.52
    ThroughAttribute
    -0.50
    rrggbb
    -0.50
    存于互联网档案馆
    -0.50
    Sucesor
    -0.49
    RetentionPolicy
    -0.48
     REV
    -0.47
    MLLoader
    -0.47
     endblock
    -0.47
    POSITIVE LOGITS
     Skyrim
    0.63
     Bethesda
    0.46
    Fallout
    0.43
    hesda
    0.43
    livion
    0.41
     Fallout
    0.41
     endorsed
    0.39
    ponses
    0.37
    
    0.37
     Morrow
    0.35
    Activations Density 0.110%

    No Known Activations