© 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. 13-GEMMASCOPE-RES-65K
    6. 14500
    Prev
    Next
    INDEX
    Explanations

    references to specific media outlets, locations, or geographic entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.79
     
    -0.71
    iconductor
    -0.68
    T
    -0.67
    F
    -0.66
    ز
    -0.64
     Sheeran
    -0.63
    UnifiedTopology
    -0.63
    แ
    -0.62
     द
    -0.61
    POSITIVE LOGITS
    Globe
    1.00
     Globe
    0.99
    }$​
    0.95
     globe
    0.93
     itſelf
    0.91
    ografija
    0.90
     myſelf
    0.89
    ſelf
    0.85
    Zitat
    0.85
     Slate
    0.85
    Activations Density 0.044%

    No Known Activations