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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 81817
    Prev
    Next
    INDEX
    Explanations

    statistical data and findings related to medical research on headaches

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

    Nigeria and Nigerian contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.57
     AssemblyTitle
    -0.55
    tonode
    -0.53
    contentLoaded
    -0.51
     Paglinawan
    -0.50
    HtmlAttribute
    -0.47
     MainAxisSize
    -0.46
    ngdoc
    -0.46
    ftagPool
    -0.46
     CreateTagHelper
    -0.45
    POSITIVE LOGITS
     Nigeria
    1.09
     Nigerian
    1.05
    Nigeria
    1.01
    Nigerian
    0.90
     Nigerians
    0.88
     NIGERIA
    0.76
     niger
    0.73
    niger
    0.61
    Niger
    0.58
     NIGER
    0.58
    Activations Density 0.012%

    No Known Activations