© 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 - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4577
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to sexual harassment claims and workplace disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maternidade
    -0.41
     libertad
    -0.36
    ↵
    -0.35
     Andersson
    -0.34
     négatif
    -0.34
     tersangka
    -0.33
    addSubview
    -0.33
    read
    -0.32
     leído
    -0.32
     aparcamiento
    -0.32
    POSITIVE LOGITS
     ModelExpression
    0.90
    contentLoaded
    0.73
     sumpay
    0.69
    ########.
    0.69
    +:+
    0.68
     AssemblyCompany
    0.68
     виправивши
    0.67
     EconPapers
    0.66
     beginnetje
    0.64
    Diwedd
    0.64
    Activations Density 0.623%

    No Known Activations