© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4000
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure elements, particularly related to file handling and multi-threading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدیا
    -0.39
    Adapun
    -0.36
     zelve
    -0.35
    舺
    -0.34
    leggen
    -0.34
    ___]
    -0.33
    GOTREF
    -0.33
    GNUC
    -0.32
     inalámbrica
    -0.32
     zaś
    -0.31
    POSITIVE LOGITS
                                   
    1.32
                                  
    0.72
    0.64
    0.63
                                 
    0.60
                                
    0.60
    -------
    0.60
    帖最后由
    0.59
    　　　　　　　　　　　　　　　　
    0.55
    0.55
    Activations Density 0.556%

    No Known Activations