Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1734
    Prev
    Next
    INDEX
    Explanations

    LaTeX syntax related to image inclusion and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.60
    tagHelperRunner
    -0.56
    期刊论文
    -0.55
    ConstraintMaker
    -0.55
    numerusform
    -0.54
     kasarigan
    -0.52
    出版年
    -0.52
    RegressionTest
    -0.52
    SharedDtor
    -0.52
     okuyayım
    -0.48
    POSITIVE LOGITS
     ويكيپيديا
    0.41
     pilot
    0.40
    /*
    0.40
     Aegean
    0.36
     bb
    0.34
    ftagPool
    0.34
    
    
    0.33
     audit
    0.32
    GTCX
    0.32
     Doctors
    0.32
    Activations Density 0.332%

    No Known Activations