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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 51728
    Prev
    Next
    INDEX
    Explanations

    references to administrative or procedural aspects of governance

    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
    DockStyle
    -0.71
    OpenHelper
    -0.47
    XmlAccessType
    -0.40
     كومونز
    -0.39
    IsContent
    -0.37
    KommentareTeilen
    -0.37
     Chwiliwch
    -0.35
     indien
    -0.34
    Organisateur
    -0.33
    TagNumber
    -0.32
    POSITIVE LOGITS
    Mvc
    0.68
    ViewFeatures
    0.65
     NUKAT
    0.58
    httphttps
    0.57
     AssemblyVersion
    0.55
    Controllers
    0.52
    ModelState
    0.49
    contentLoaded
    0.48
    isContained
    0.48
    Хьажоргаш
    0.47
    Activations Density 0.000%

    No Known Activations