Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11292
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to court proceedings

    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
     Савезне
    -1.22
     Administrativna
    -0.96
     Italijanski
    -0.86
    Personensuche
    -0.85
    featureID
    -0.85
     Мексичка
    -0.80
    GEBURTSDATUM
    -0.80
    SourceChecksum
    -0.75
    AISSEE
    -0.75
     betweenstory
    -0.74
    POSITIVE LOGITS
     rayons
    0.33
     FontWeight
    0.32
     NoSuch
    0.30
     binh
    0.30
     prace
    0.29
    cesso
    0.28
    WEET
    0.28
    setcounter
    0.28
     rojas
    0.28
     {{\
    0.28
    Activations Density 18.812%

    No Known Activations