© 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. 2-GEMMASCOPE-RES-16K
    11. 3484
    Prev
    Next
    INDEX
    Explanations

    the term "exception" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.45
     orgánico
    -0.38
     ['./
    -0.38
    ⟬
    -0.37
    ELTS
    -0.37
    lüğü
    -0.34
     Gemeinder
    -0.34
     Vermögen
    -0.34
    ampunk
    -0.33
     igång
    -0.33
    POSITIVE LOGITS
     exception
    4.56
     exceptions
    3.88
     Exceptions
    3.36
     Exception
    3.34
    exception
    3.33
     excepción
    3.09
     excep
    2.89
    Exceptions
    2.78
    exceptions
    2.75
    Exception
    2.66
    Activations Density 0.189%

    No Known Activations