© 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. 38-GEMMASCOPE-RES-16K
    6. 9287
    Prev
    Next
    INDEX
    Explanations

    indicators of a technical or software-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     می‌توان
    -0.91
     coö
    -0.83
     می‌توانید
    -0.76
     می‌ده
    -0.73
     می‌تواند
    -0.70
     نمی‌
    -0.69
    ‌ای
    -0.67
     می‌کند
    -0.66
     می‌شود
    -0.65
     می‌شوند
    -0.64
    POSITIVE LOGITS
     tambin
    0.50
     argint
    0.49
     dumne
    0.46
     prieten
    0.46
     henkil
    0.46
     varandra
    0.45
     Bucure
    0.43
     humanidad
    0.42
     singur
    0.42
     Suomessa
    0.42
    Activations Density 0.775%

    No Known Activations