© 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. 3-GEMMASCOPE-RES-16K
    11. 5407
    Prev
    Next
    INDEX
    Explanations

    terms related to programming errors and exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    abbreviated technical or scientific terms, particularly those related to errors, protocols, or computing standards.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @jbloomaus
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessFile
    -0.80
     nahilalakip
    -0.74
     mapStateToProps
    -0.73
    cydow
    -0.69
    mapStateToProps
    -0.66
    endphp
    -0.65
    مصادر
    -0.63
    anias
    -0.62
    winston
    -0.61
    ANDUM
    -0.60
    POSITIVE LOGITS
     EG
    1.11
     Eb
    1.09
     Egger
    1.07
     ECS
    1.07
     Esk
    1.06
     EB
    1.02
     EK
    1.02
     EA
    1.00
     Estrada
    0.99
     Ema
    0.99
    Activations Density 0.835%

    No Known Activations