© 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. 20-GEMMASCOPE-RES-16K
    11. 11043
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures, particularly focusing on error handling and object parsing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.85
    AccessorTable
    -0.81
    MessageOf
    -0.77
     betweenstory
    -0.73
     مرئيه
    -0.73
    featureID
    -0.72
    EDEFAULT
    -0.70
     propOrder
    -0.65
     Италијани
    -0.65
     queſta
    -0.64
    POSITIVE LOGITS
     unique
    0.39
     whose
    0.38
     here
    0.38
     reported
    0.37
    Ar
    0.34
     Ar
    0.34
    iiiiiiii
    0.33
    iiiii
    0.32
     represented
    0.31
    whose
    0.31
    Activations Density 0.284%

    No Known Activations