© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6576
    Prev
    Next
    INDEX
    Explanations

    references to specific programming languages, particularly in relation to web development

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

    programming languages or frameworks

    np_acts-logits-general · gemini-2.0-flash

    programming languages and frameworks

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    webElementXpaths
    -0.72
    setVerticalGroup
    -0.60
    期刊论文
    -0.53
     <=",
    -0.51
     محفوظة
    -0.49
    twimg
    -0.48
    extAlignment
    -0.46
    VYMaps
    -0.46
    RegressionTest
    -0.46
    complexType
    -0.45
    POSITIVE LOGITS
     technologies
    0.56
     architectures
    0.53
     software
    0.53
     frameworks
    0.52
     technology
    0.51
     piattaforma
    0.49
     ecosystem
    0.49
     platforms
    0.48
     softwares
    0.47
     architecture
    0.47
    Activations Density 0.562%

    No Known Activations