© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 40665
    Prev
    Next
    INDEX
    Explanations

    definitions and references related to game entities and actions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    creature accessors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.56
     gyhoeddwyd
    -0.53
     Obrador
    -0.50
    //</
    -0.50
     plebis
    -0.49
     հղումներ
    -0.48
    存于互联网档案馆
    -0.48
     récolte
    -0.48
    ftagPool
    -0.47
    ştır
    -0.47
    POSITIVE LOGITS
    новништво
    0.47
    tanleria
    0.35
    gameserver
    0.35
     createSprite
    0.35
    fabri
    0.34
     vulgaris
    0.33
     kogo
    0.32
     Soldier
    0.32
    UserModel
    0.32
     سكانية
    0.31
    Activations Density 0.029%

    No Known Activations