© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 5442
    Prev
    Next
    INDEX
    Explanations

    code-related terms and constructs, particularly those related to asynchronous programming in Java

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

    C code or concurrency

    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
    AndEndTag
    -0.72
     snippetHide
    -0.64
    SqlClient
    -0.60
     SafeMath
    -0.55
    Šaltiniai
    -0.54
     AssemblyVersion
    -0.53
     getItemCount
    -0.53
    Autoritní
    -0.52
    astify
    -0.52
    تقاوى
    -0.51
    POSITIVE LOGITS
    tableFuture
    0.61
    behind
    0.42
     behind
    0.39
    Behind
    0.39
     Behind
    0.38
    ExecutorService
    0.36
    ParallelGroup
    0.36
    better
    0.33
     dominar
    0.31
    sibility
    0.31
    Activations Density 0.002%

    No Known Activations