© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8747
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the significance or necessity of particular concepts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.50
    限り
    -0.45
     estético
    -0.44
     húmedo
    -0.43
    Morfologia
    -0.43
     libremente
    -0.41
     poète
    -0.41
    +#+
    -0.40
     mecánico
    -0.40
     affiche
    -0.39
    POSITIVE LOGITS
     important
    2.88
    important
    2.69
     crucial
    2.69
     Important
    2.56
    Important
    2.52
     vital
    2.36
     penting
    2.11
     essential
    2.09
     Crucial
    2.06
     중요
    2.05
    Activations Density 0.190%

    No Known Activations