© 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. 25-GEMMASCOPE-RES-16K
    11. 15170
    Prev
    Next
    INDEX
    Explanations

    introductory sections or headings in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     defaultstate
    -0.77
    تقاوى
    -0.73
    ंदीखरीदारी
    -0.59
     незавершена
    -0.58
     betweenstory
    -0.56
     @"/
    -0.56
    
    -0.55
    下载附件
    -0.53
     Савезне
    -0.53
     мәкал
    -0.52
    POSITIVE LOGITS
     mach
    0.44
    struts
    0.44
     MACH
    0.41
     ventilation
    0.41
     nuisance
    0.40
     overhang
    0.40
     HANG
    0.39
     Unwin
    0.39
     programming
    0.39
     edges
    0.38
    Activations Density 0.141%

    No Known Activations