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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7483
    Prev
    Next
    INDEX
    Explanations

    references to various types of artillery and projectile weapons

    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
    rungsseite
    -0.67
    ImageContext
    -0.63
    MigrationBuilder
    -0.58
    jsxFileName
    -0.56
     архивлан
    -0.56
     StatefulWidget
    -0.55
     NgModule
    -0.53
    Parcelize
    -0.50
    webElementGuid
    -0.50
     Audiodateien
    -0.49
    POSITIVE LOGITS
     artillery
    1.00
     Artillery
    0.88
     cannon
    0.56
     cannons
    0.54
    tillerie
    0.51
     firing
    0.50
     gunner
    0.49
    砲
    0.48
    炮
    0.48
     fired
    0.46
    Activations Density 0.009%

    No Known Activations