© 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. 9647
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical or programming expressions, especially focusing on specific symbols and identifiers

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

    Mathematical formulas or expressions

    np_acts-logits-general · gemini-2.0-flash

    file paths and division

    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
     ExecuteAsync
    -0.56
    AndEndTag
    -0.56
    CloseOperation
    -0.53
     <=",
    -0.52
    IContainer
    -0.52
    SourceChecksum
    -0.52
    
    -0.52
    cshtml
    -0.50
    ContentAsync
    -0.48
    ьаж
    -0.48
    POSITIVE LOGITS
    /
    1.60
     /
    1.19
    ()/
    0.89
    ／
    0.86
    /(
    0.80
    '/
    0.80
    /?
    0.78
    /,
    0.78
     $/
    0.77
    /{
    0.76
    Activations Density 0.285%

    No Known Activations