© 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. 53546
    Prev
    Next
    INDEX
    Explanations

    technical specifications and parameters in programming or data context

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

    mathematical symbols and greek letters

    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
    GEBURTSDATUM
    -0.96
     gyhoeddwyd
    -0.79
    GraphicsUnit
    -0.77
    fromnode
    -0.76
    تقاوى
    -0.76
    tonode
    -0.76
    AndEndTag
    -0.75
    Personendaten
    -0.75
    
    -0.75
    ︲
    -0.73
    POSITIVE LOGITS
     corrientes
    0.23
     betyr
    0.23
     redacción
    0.21
     abundancia
    0.20
     tarko
    0.20
     confusión
    0.19
    ntö
    0.19
     eliminación
    0.19
    Presented
    0.19
     betyder
    0.19
    Activations Density 0.052%

    No Known Activations