© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 15488
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate encountering an error or exception in programming code

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

    error messages and exception descriptions in technical code and debugging contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     useAppContext
    -0.46
    autoreleasepool
    -0.45
     autorytatywna
    -0.42
    jenner
    -0.42
    Personendaten
    -0.42
    ServiceTest
    -0.41
    NameInMap
    -0.39
     disponibilités
    -0.39
     Taktlose
    -0.37
    MigrationBuilder
    -0.37
    POSITIVE LOGITS
     error
    1.45
     errors
    1.23
     Error
    1.17
    error
    1.10
    エラー
    1.08
     Errors
    1.05
     Fehler
    0.98
    报错
    0.98
    Error
    0.95
    errors
    0.95
    Activations Density 0.754%

    No Known Activations