Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 103148
    Prev
    Next
    INDEX
    Explanations

    closing brackets and related syntax elements in code

    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
    transQ
    -0.70
    нгред
    -0.68
     gynhyrchwyd
    -0.66
    httphttps
    -0.65
     ffilm
    -0.65
    🇶
    -0.63
     geſch
    -0.62
     myſelf
    -0.62
     فريبيس
    -0.61
     betweenstory
    -0.61
    POSITIVE LOGITS
     defaultstate
    0.31
    före
    0.29
     listening
    0.29
     ricev
    0.28
    jangkau
    0.27
    getActive
    0.27
    所得
    0.26
     leyendo
    0.25
     forget
    0.24
    Forget
    0.24
    Activations Density 0.012%

    No Known Activations