© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4436
    Prev
    Next
    INDEX
    Explanations

    HTTP request methods and content type specifications

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

    terms and attributes related to web and application development, especially those specifying content type, data format, layout properties, and methods used in web APIs and UI frameworks.

    oai_token-act-pair · gpt-4.1-2025-04-14Triggered by @ywhp2c8tjm

    snippets of code containing web-related keywords such as content type and request methods like GET, POST or JSON, often associated with web technologies or data formats.

    oai_token-act-pair · gemini-2.0-flashTriggered by @ywhp2c8tjm

    HTML style attributes

    np_acts-logits-general · gemini-2.0-flash

    CSS and HTML positioning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    
    -0.91
     Geiſt
    -0.91
     queſta
    -0.91
    
    -0.90
    
    -0.89
    <unused17>
    -0.88
    
    -0.88
    <unused15>
    -0.88
    
    -0.88
    <unused3>
    -0.88
    POSITIVE LOGITS
    findpost
    0.33
    ,
    0.29
     following
    0.28
     recently
    0.27
     Eing
    0.26
    気がする
    0.24
     relative
    0.23
     filles
    0.22
    RDONLY
    0.21
     Bauch
    0.21
    Activations Density 0.162%

    No Known Activations