© 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. 37984
    Prev
    Next
    INDEX
    Explanations

    mentions of image file formats, particularly PNG

    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
     CreateTagHelper
    -1.11
    makeConstraints
    -0.96
    mybatisplus
    -0.95
    +#+#
    -0.94
    WebVitals
    -0.91
    !*\
    -0.90
    __':
    
    -0.90
     referenties
    -0.82
    __':
    -0.82
    évaluateur
    -0.81
    POSITIVE LOGITS
    png
    1.82
     png
    1.48
     PNG
    1.35
    PNG
    1.34
    jpg
    0.74
    pong
    0.73
     Hansen
    0.71
     bong
    0.71
     nélk
    0.70
     LNG
    0.70
    Activations Density 0.013%

    No Known Activations