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. 2135
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to NMR (nuclear magnetic resonance) spectroscopy and its application in studies involving lipids and proteins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    NMR spectroscopy studies

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    UrlResolution
    -0.75
    astify
    -0.71
     FetchType
    -0.68
     nonUne
    -0.68
     EconPapers
    -0.68
    ="@+
    -0.65
    ConstraintMaker
    -0.64
    ArgumentParser
    -0.61
     ***!
    -0.59
     queſta
    -0.59
    POSITIVE LOGITS
     test
    0.32
     tunn
    0.30
     monitor
    0.30
     crew
    0.29
     про
    0.29
     perdana
    0.28
     linh
    0.28
     measuring
    0.28
     sc
    0.28
     slot
    0.27
    Activations Density 0.152%

    No Known Activations