© 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. 28-GEMMASCOPE-RES-16K
    11. 8017
    Prev
    Next
    INDEX
    Explanations

    references to regulatory bodies and actions within the context of audits and financial oversight

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

    the UK or Britain

    np_acts-logits-general · gemini-2.0-flash

    British institutions and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ɚ
    -0.70
     uș
    -0.66
     maș
    -0.66
     idéia
    -0.66
     creș
    -0.65
     argint
    -0.63
     confiable
    -0.62
    hitheater
    -0.61
     financiamiento
    -0.60
     econômica
    -0.60
    POSITIVE LOGITS
     UK
    1.43
     £
    1.31
     Britain
    1.27
     British
    1.27
    英国
    1.26
    -£
    1.23
    UK
    1.23
     England
    1.18
     London
    1.16
    British
    1.16
    Activations Density 2.055%

    No Known Activations