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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122662
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to object creation and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     utafitiHapana
    -0.57
     XCTest
    -0.57
     հղումներ
    -0.56
    istoitu
    -0.55
    +#+
    -0.55
    CppMethod
    -0.55
     '\\;'
    -0.54
    ContentLoaded
    -0.53
     Wikimedijinoj
    -0.53
    detectChanges
    -0.53
    POSITIVE LOGITS
    wesen
    0.37
     obstante
    0.37
     Apabila
    0.36
    Verkehr
    0.35
     secundarios
    0.35
     asimismo
    0.34
     igualmente
    0.32
     resourceCulture
    0.31
    logOut
    0.31
     Nusantara
    0.31
    Activations Density 0.043%

    No Known Activations