© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 9225
    Prev
    Next
    INDEX
    Explanations

    syntactic structure and elements related to data processing or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.79
     protoimpl
    -0.76
    脚注の使い方
    -0.68
     '\\;'
    -0.64
     Мексичка
    -0.62
    Šaltiniai
    -0.61
     kasarigan
    -0.60
    NameValuePair
    -0.56
    matchCondition
    -0.55
    NgModule
    -0.55
    POSITIVE LOGITS
     wireType
    0.65
     rhestr
    0.55
    âmara
    0.55
    ειτουργ
    0.55
    bolista
    0.53
    jsonwebtoken
    0.51
     lira
    0.51
    uckland
    0.50
    umenter
    0.49
     chi̍t
    0.48
    Activations Density 3.945%

    No Known Activations