© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 9040
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions related to mechanical systems and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exult
    -0.68
     rejoiced
    -0.67
     rejoice
    -0.63
     rejoicing
    -0.61
     joyous
    -0.60
     happiness
    -0.60
     gladness
    -0.59
     glorious
    -0.59
     delightful
    -0.59
     joyfully
    -0.59
    POSITIVE LOGITS
     failures
    1.19
     failure
    1.15
     incorrect
    1.11
     failed
    1.08
     wrong
    1.08
     Incorrect
    1.02
     faulty
    1.02
     defective
    1.01
     failing
    1.00
     Failure
    1.00
    Activations Density 5.799%

    No Known Activations