© 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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6679
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to programming, data handling, and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "));
    
    -1.55
    "):
    
    -1.48
    '));
    
    -1.47
    '):
    
    -1.46
    '),
    
    -1.41
    "]);
    
    -1.38
    "),
    
    -1.36
    '))
    
    -1.33
    ')):
    -1.32
    ")){
    
    -1.30
    POSITIVE LOGITS
     arşivlendi
    0.47
    ,"
    0.45
    )
    0.40
    tiéndose
    0.39
    ,'
    0.38
    crollView
    0.37
    IsPostBack
    0.35
     ferons
    0.35
     HasFactory
    0.34
     становника
    0.34
    Activations Density 0.674%

    No Known Activations