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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 20339
    Prev
    Next
    INDEX
    Explanations

    technical terms and functionalities related to Java Swing event handling and component management

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

    javax.swing.border and event handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.44
    jsxFileName
    -0.39
    mper
    -0.39
    حياته
    -0.38
    hts
    -0.38
    awaiter
    -0.38
    <0xEA>
    -0.37
    ChromeDriver
    -0.37
    plevel
    -0.37
    ModelMap
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.59
     eşofman
    0.55
    astify
    0.53
    AsUp
    0.52
     referrerpolicy
    0.52
     NSCoder
    0.51
     belangrij
    0.51
     InputDecoration
    0.47
     Мексичка
    0.47
     wikipagina
    0.47
    Activations Density 0.014%

    No Known Activations