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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 7476
    Prev
    Next
    INDEX
    Explanations

    references to government agencies and legal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actualidad
    -0.29
     personnalité
    -0.26
    extérieur
    -0.26
     allgemeine
    -0.24
     enfance
    -0.24
     Vergangenheit
    -0.23
     Öffentlichkeit
    -0.22
     sayfas
    -0.21
    utama
    -0.21
     internasional
    -0.21
    POSITIVE LOGITS
     efforts
    1.14
    efforts
    1.11
     ब्रेकडाउन
    1.07
     effort
    1.05
     manipulations
    1.03
     attempts
    1.02
     Efforts
    1.02
     actions
    1.00
     attempt
    1.00
     interactions
    0.96
    Activations Density 1.342%

    No Known Activations