© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 10514
    Prev
    Next
    INDEX
    Explanations

    terms related to quantification and quantization in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usty
    -0.59
    hasErrors
    -0.52
     Negoti
    -0.52
    Ārējās
    -0.51
    ORN
    -0.50
     khuy
    -0.50
     '".$
    -0.50
    ='".$
    -0.50
    zadas
    -0.49
     Borg
    -0.49
    POSITIVE LOGITS
    脚注の使い方
    0.95
     الحره
    0.92
    hyd
    0.82
    setVerticalGroup
    0.77
     hyd
    0.75
    AsUp
    0.75
    ashir
    0.75
    __':
    
    0.73
    quanti
    0.70
    ificance
    0.69
    Activations Density 0.106%

    No Known Activations