© 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. 11-GEMMASCOPE-RES-16K
    11. 8554
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong negative emotions or distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
     yoksa
    -0.47
    vimos
    -0.46
     Pueden
    -0.44
    ställ
    -0.43
    不做
    -0.42
     sugiere
    -0.42
    něž
    -0.42
    তথ্যসূত্র
    -0.41
     catedral
    -0.41
     gärna
    -0.41
    POSITIVE LOGITS
     мәкал
    0.60
    astify
    0.54
    ngrx
    0.52
    keyColumn
    0.51
    
    0.46
    typeorm
    0.44
    msgTypes
    0.44
     impe
    0.43
    AnchorTagHelper
    0.43
    roves
    0.43
    Activations Density 0.319%

    No Known Activations