© 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. 10-GEMMASCOPE-RES-16K
    11. 5906
    Prev
    Next
    INDEX
    Explanations

    expressions of bravery and courage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.65
     MainAxisSize
    -0.54
     INTERESAR
    -0.53
    曖昧さ回避
    -0.50
     متحده
    -0.50
    MethodManager
    -0.49
    ngrx
    -0.48
    haustible
    -0.48
    uled
    -0.47
    elemField
    -0.47
    POSITIVE LOGITS
     daring
    1.45
     bold
    1.24
     dared
    1.22
     berani
    1.16
     dares
    1.15
     bolder
    1.14
     boldly
    1.14
     dare
    1.12
     courageous
    1.10
     Bold
    1.08
    Activations Density 0.263%

    No Known Activations