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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10599
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to MVC architecture and web development frameworks

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

    ASP.NET MVC code snippets

    np_acts-logits-general · gemini-2.0-flash

    ASP.NET MVC actions and views

    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
    azz
    -0.31
     Tirol
    -0.31
    ysio
    -0.30
     Ketten
    -0.29
     Spector
    -0.29
     immediately
    -0.29
     befe
    -0.29
    External
    -0.28
     besk
    -0.28
     Mombasa
    -0.28
    POSITIVE LOGITS
     समीक्षाओं
    0.66
    AddTagHelper
    0.63
    tagHelperRunner
    0.62
    fjspx
    0.62
    expandindo
    0.57
    
    0.57
    tagHelper
    0.54
    GraphicsUnit
    0.53
     MainAxisSize
    0.52
    InjectAttribute
    0.52
    Activations Density 0.134%

    No Known Activations