© 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. 14025
    Prev
    Next
    INDEX
    Explanations

    indications of errors or failure states in code related to system operations

    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
     Ellos
    -0.57
     asegurarse
    -0.50
    :{
    -0.49
    esterno
    -0.48
     Proper
    -0.47
    Demografia
    -0.47
     pastic
    -0.47
     disponibilités
    -0.46
    Transkript
    -0.46
     Agust
    -0.46
    POSITIVE LOGITS
    └──
    0.70
    Hozzáférés
    0.70
    áñez
    0.70
    mitian
    0.69
    )':
    0.68
     Wikimedijinoj
    0.67
     AssemblyProduct
    0.66
     sebagainya
    0.65
     dieux
    0.64
     Himo
    0.63
    Activations Density 0.027%

    No Known Activations