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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84455
    Prev
    Next
    INDEX
    Explanations

    references to cytokines and inflammation in the context of stem cell research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brinquedos
    -0.37
     Instrumente
    -0.36
     mattino
    -0.35
     strumento
    -0.35
     autorytatywna
    -0.33
     fören
    -0.33
     hombros
    -0.33
     Vereine
    -0.33
     hujan
    -0.33
    sätzlich
    -0.32
    POSITIVE LOGITS
    ValueStyle
    0.61
     CWE
    0.59
    Geplaatst
    0.56
    
    0.55
     AssemblyCulture
    0.50
    evos
    0.49
    MLLoader
    0.48
    onAttach
    0.48
    koning
    0.47
    Географија
    0.46
    Activations Density 0.261%

    No Known Activations