© 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. 119814
    Prev
    Next
    INDEX
    Explanations

    references to the English language and its usage in various contexts

    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
    endpush
    -0.56
    Viited
    -0.55
     مشين
    -0.53
    initComponents
    -0.50
     désactiv
    -0.48
    ftagPool
    -0.48
     alamu
    -0.48
    MockBean
    -0.47
     McAllister
    -0.47
    richTextPanel
    -0.47
    POSITIVE LOGITS
    Language
    0.46
    language
    0.45
     język
    0.45
     language
    0.45
     Language
    0.44
    脚注の使い方
    0.41
    зык
    0.38
     Languages
    0.37
     languages
    0.36
    englanniksi
    0.36
    Activations Density 0.005%

    No Known Activations