© 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. 14493
    Prev
    Next
    INDEX
    Explanations

    details regarding instructions, critiques, or clarifications related to a process or project

    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
     AssemblyCulture
    -0.77
    Portale
    -0.68
    GetEnumerator
    -0.66
    
    -0.65
    anskje
    -0.65
    abetes
    -0.65
    twimg
    -0.64
    prefixer
    -0.59
    ็จ
    -0.58
    openzeppelin
    -0.58
    POSITIVE LOGITS
    Архівовано
    0.58
    "]);
    
    0.57
    ")));
    
    0.56
     }{@
    0.55
     ši
    0.54
     gynhyrchwyd
    0.52
     only
    0.51
    "])
    
    0.50
     विश्वसनीयता
    0.50
    QMetaType
    0.49
    Activations Density 0.152%

    No Known Activations