© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105812
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "mage" and associated actions or concepts in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    NameInMap
    -0.60
     HasFactory
    -0.55
    出版年
    -0.55
    tvguidetime
    -0.53
     institutional
    -0.51
    webElement
    -0.50
     Bina
    -0.50
     Kina
    -0.49
     Andrei
    -0.48
     становника
    -0.48
    POSITIVE LOGITS
     Hongrie
    0.35
     castillo
    0.35
    mybatisplus
    0.31
    prepareStatement
    0.30
     castle
    0.30
    lusconi
    0.29
    >`;
    0.29
     IBOutlet
    0.29
    日閲覧
    0.29
     Egyp
    0.28
    Activations Density 0.001%

    No Known Activations