© 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. 20-GEMMASCOPE-RES-131K
    11. 58609
    Prev
    Next
    INDEX
    Explanations

    terms related to DOM (Document Object Model) manipulation in JavaScript

    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
    多谢
    -0.34
     Köl
    -0.33
    一點
    -0.33
     istore
    -0.33
     maaaring
    -0.32
     pytest
    -0.31
     Alquiler
    -0.31
     gás
    -0.31
     klara
    -0.30
    美国的
    -0.30
    POSITIVE LOGITS
    Personendaten
    0.86
    nativeElement
    0.72
    UnusedPrivate
    0.69
    parsedMessage
    0.68
    yntaxException
    0.66
     GenerationType
    0.62
    IntoConstraints
    0.62
    errHandler
    0.57
    BeginContext
    0.57
    webElement
    0.56
    Activations Density 0.001%

    No Known Activations