© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 1701
    Prev
    Next
    INDEX
    Explanations

    elements related to data handling and structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    спита
    -0.36
    今から
    -0.36
     
    -0.36
     of
    -0.36
     or
    -0.35
     I
    -0.34
    bestimm
    -0.34
     me
    -0.33
     over
    -0.33
     and
    -0.33
    POSITIVE LOGITS
     InputDecoration
    1.26
     propOrder
    1.10
    ",{
    1.02
     المعيارى
    1.00
    
    0.96
    ":{
    0.94
    ':{
    0.94
    ',{
    0.94
     IndexPath
    0.91
     StatelessWidget
    0.90
    Activations Density 0.385%

    No Known Activations