© 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. 20-GEMMASCOPE-RES-131K
    11. 67102
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to features, leadership, body language, communication, modulation, symptoms, statistical methods, antiviral responses, diffusion, long-term monitoring, single photon sources, leakage currents, duty cycle correction, heat transport, and emotional influences

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

    measurement and analysis terms

    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
     ویکی‌پدی
    -0.66
     للمعارف
    -0.56
     мәкал
    -0.52
    PerformLayout
    -0.51
     المعيارى
    -0.51
     tartalomajánló
    -0.50
     calendriers
    -0.50
     चीज़ों
    -0.49
    WriteBarrier
    -0.49
    ">@
    -0.48
    POSITIVE LOGITS
     tarko
    0.43
     cuchara
    0.42
    allows
    0.41
     mahdol
    0.41
     propuesto
    0.41
     же
    0.40
     permettra
    0.40
     allows
    0.40
     enseña
    0.40
     permitido
    0.40
    Activations Density 0.068%

    No Known Activations