© 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. 14876
    Prev
    Next
    INDEX
    Explanations

    references to standards and specifications, particularly related to ASTM and technical documents in scientific contexts

    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
    AccessorTable
    -1.14
    tagHelperRunner
    -0.87
     للمعارف
    -0.87
    ViewFeatures
    -0.87
    AddTagHelper
    -0.85
    存于互联网档案馆
    -0.82
    новниш
    -0.82
    isContained
    -0.81
    Personensuche
    -0.80
     protoimpl
    -0.80
    POSITIVE LOGITS
    BeginContext
    0.51
     محفوظة
    0.49
     
    0.46
     curé
    0.45
     CURLOPT
    0.44
    円で
    0.42
     Romains
    0.42
    idue
    0.42
    पन
    0.41
     ISO
    0.41
    Activations Density 0.815%

    No Known Activations