© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101469
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to equations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     AssemblyCulture
    -0.49
     defaultstate
    -0.48
    下载附件
    -0.48
    eliner
    -0.47
    contentLoaded
    -0.46
    zegovina
    -0.45
     TestBed
    -0.45
    kaŭ
    -0.44
    atonin
    -0.42
    WriteTagHelper
    -0.42
    POSITIVE LOGITS
     lenker
    0.47
     समीक्षक
    0.41
    irited
    0.41
    comuna
    0.39
     ModelExpression
    0.37
    umab
    0.35
     sessions
    0.35
     urma
    0.34
     segnal
    0.34
    vedad
    0.33
    Activations Density 0.026%

    No Known Activations