© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86267
    Prev
    Next
    INDEX
    Explanations

    code structure and definitions in programming languages, particularly related to functions and API requests

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

    code structure containing String and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    CppMethod
    -0.77
    AnimationsModule
    -0.62
     snippetHide
    -0.61
    脚注の使い方
    -0.60
     AssemblyCompany
    -0.59
    rungsseite
    -0.56
    WriteBarrier
    -0.55
    UnusedPrivate
    -0.54
    __':
    -0.54
     Infór
    -0.52
    POSITIVE LOGITS
     pedest
    0.41
     mean
    0.40
    室
    0.38
     trac
    0.38
    行
    0.38
     easy
    0.37
     ins
    0.37
    底
    0.37
     Easy
    0.37
     sov
    0.36
    Activations Density 0.360%

    No Known Activations