© 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. 10298
    Prev
    Next
    INDEX
    Explanations

    references to various versions and components of the .NET framework and related technologies

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

    ".NET Core" or "AspNetCore" occurrences

    np_acts-logits-general · gemini-2.0-flash

    ASP.NET Core programming

    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
     le
    -0.35
     viz
    -0.35
    JSONException
    -0.33
     Travers
    -0.31
     swims
    -0.30
     Cu
    -0.30
     cellulare
    -0.29
     ο
    -0.29
     cu
    -0.28
     γ
    -0.28
    POSITIVE LOGITS
    AspNetCore
    1.57
     AspNetCore
    0.98
    IUrlHelper
    0.93
     للمعارف
    0.85
     ActivatedRoute
    0.85
    ſelf
    0.82
     TestBed
    0.81
     queſta
    0.80
     myſelf
    0.80
    ſcher
    0.74
    Activations Density 0.010%

    No Known Activations