© 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. 33-GEMMASCOPE-RES-16K
    11. 1188
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and functions related to programming logic and output handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.54
    ArrowToggle
    -0.40
    الإنجليزية
    -0.38
    CppMethod
    -0.38
    esModule
    -0.38
    MigrationBuilder
    -0.36
     useCallback
    -0.36
    WithIdentifier
    -0.33
     Zak
    -0.33
    ślę
    -0.33
    POSITIVE LOGITS
     display
    1.90
     print
    1.81
     printing
    1.77
     displaying
    1.70
     Display
    1.69
     Print
    1.66
     displayed
    1.65
     printed
    1.63
     prints
    1.60
    display
    1.56
    Activations Density 0.753%

    No Known Activations