© 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. 15-GEMMASCOPE-RES-16K
    11. 1934
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to mechanisms and techniques in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.62
    BorderFactory
    -0.59
     fubject
    -0.55
     vérit
    -0.54
     Bielefeld
    -0.53
     فريبيس
    -0.50
    
    -0.50
     Utara
    -0.49
    URLException
    -0.49
     Jefus
    -0.49
    POSITIVE LOGITS
     mechanism
    0.67
     schemes
    0.65
     mechanisms
    0.65
    scheme
    0.65
     interventions
    0.63
    mechanism
    0.63
    Mechanism
    0.63
    Mechanisms
    0.62
     Mechanisms
    0.61
     Mechanism
    0.60
    Activations Density 0.275%

    No Known Activations