© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 125067
    Prev
    Next
    INDEX
    Explanations

    occurrences of structured or formal statements in legal or official contexts

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

    legalistic foreign terms

    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
    Tikang
    -0.74
    tagHelperRunner
    -0.70
    TagMode
    -0.68
    httphttps
    -0.63
     Taktlose
    -0.62
    webElementXpaths
    -0.60
     للمعارف
    -0.59
     <=",
    -0.58
    LabelTagHelper
    -0.57
    TestingModule
    -0.57
    POSITIVE LOGITS
     exportación
    0.36
     assured
    0.33
     promozione
    0.32
     assic
    0.32
     hablaba
    0.30
    hésite
    0.30
     étranger
    0.30
     tournée
    0.29
     juridique
    0.29
    ių
    0.29
    Activations Density 0.033%

    No Known Activations