© 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. 37-GEMMASCOPE-RES-16K
    11. 4509
    Prev
    Next
    INDEX
    Explanations

    terms related to game mechanics, specifically focusing on mana and healing abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.55
    Tembelea
    -0.52
    Personensuche
    -0.48
     Wikimedijinoj
    -0.48
    sidemargin
    -0.47
    apimachinery
    -0.47
    TagMode
    -0.45
     ComVisible
    -0.44
    IndentedString
    -0.44
    ChildScrollView
    -0.43
    POSITIVE LOGITS
     bonus
    0.71
     bonuses
    0.68
     cooldown
    0.66
     triggered
    0.64
     triggers
    0.63
     effect
    0.63
     unlocked
    0.62
     unlock
    0.61
     bugged
    0.60
     otorg
    0.59
    Activations Density 0.324%

    No Known Activations