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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6228
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific coding elements related to building and managing content structures

    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
     viewType
    -0.84
     kaarangay
    -0.78
     ویکی‌پدیا
    -0.77
    EndGlobalSection
    -0.76
     Signalez
    -0.73
    Personendaten
    -0.72
    IonicModule
    -0.68
     StatefulWidget
    -0.67
    GRANTED
    -0.66
     esternos
    -0.65
    POSITIVE LOGITS
    ={({
    0.55
    ərbaycan
    0.50
     predecess
    0.50
     regi
    0.46
     platt
    0.45
     ap
    0.45
     clic
    0.44
    PhysRevLett
    0.44
    clic
    0.44
     offens
    0.43
    Activations Density 0.787%

    No Known Activations