Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15343
    Prev
    Next
    INDEX
    Explanations

    the keyword "Application" and its contexts related to software or programming concepts

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

    "Application"

    np_acts-logits-general · gemini-2.0-flash

    application in software contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.39
     EconPapers
    -0.39
     Numerade
    -0.38
    
    -0.38
    Ƚ
    -0.36
     Paix
    -0.35
    Jîn
    -0.34
    umumkan
    -0.34
    夠
    -0.33
     nakalista
    -0.33
    POSITIVE LOGITS
    AutoScaleMode
    0.63
     Application
    0.58
    likation
    0.56
     UIApplication
    0.56
    FieldBuilder
    0.53
     WebApplication
    0.53
     defaultstate
    0.51
     application
    0.51
    plication
    0.50
     ImageIcon
    0.50
    Activations Density 0.078%

    No Known Activations