© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 14523
    Prev
    Next
    INDEX
    Explanations

    terms related to institutions and institutional frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cristiana
    -0.90
     Waray
    -0.89
     cargoes
    -0.87
     Mercan
    -0.86
     Feria
    -0.85
     Genocide
    -0.85
     Uff
    -0.84
     Telex
    -0.82
     Honeywell
    -0.82
     Garry
    -0.82
    POSITIVE LOGITS
     Institute
    1.29
     institute
    1.17
     Institutes
    1.16
     institutions
    1.12
     institutes
    1.12
     institution
    1.11
    Institute
    1.07
     INSTIT
    1.02
    INST
    1.01
     Institution
    1.01
    Activations Density 0.084%

    No Known Activations