© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 4692
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to JSON data handling and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RenderAtEndOf
    -0.54
     TestBed
    -0.51
    RunWith
    -0.50
    wpi
    -0.50
    ViewInit
    -0.50
    ContentAsync
    -0.49
    TagMode
    -0.48
     getRule
    -0.47
    providedIn
    -0.46
    ExtendWith
    -0.45
    POSITIVE LOGITS
    fastjson
    4.03
    toJSONString
    0.85
    mybatisplus
    0.66
    Gson
    0.62
     Gson
    0.57
    JSON
    0.56
    ObjectMapper
    0.56
     JSON
    0.55
    json
    0.55
    jackson
    0.53
    Activations Density 0.000%

    No Known Activations