© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 9594
    Prev
    Next
    INDEX
    Explanations

    code elements related to variable assignment and data retrieval in programming

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

    Code and data assignment/mathematical operations

    np_acts-logits-general · gemini-2.0-flash

    code parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HasKey
    -0.39
    adaptiveStyles
    -0.38
     AppColors
    -0.36
     <>",
    -0.35
    ніципалі
    -0.35
     Wikimedijinoj
    -0.33
     OSError
    -0.32
    Gön
    -0.32
    ContentLoaded
    -0.31
    WithIOException
    -0.31
    POSITIVE LOGITS
    
    0.52
    átula
    0.50
    RetentionPolicy
    0.50
    énario
    0.49
    tonsoft
    0.48
    saco
    0.47
    MetaData
    0.47
     Sheila
    0.46
     Hutchins
    0.46
    hner
    0.45
    Activations Density 0.218%

    No Known Activations