© 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. 85206
    Prev
    Next
    INDEX
    Explanations

    economic terms and concepts related to business and compliance

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

    economic, legal, and social contexts

    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
     initComponents
    -0.43
    rrggbb
    -0.38
    verifyException
    -0.37
     linkovi
    -0.36
    printStackTrace
    -0.34
     intptr
    -0.34
    spesies
    -0.32
    WebVitals
    -0.32
    geslacht
    -0.31
    锈钢
    -0.31
    POSITIVE LOGITS
     AssemblyCompany
    0.59
     economies
    0.51
    icksburg
    0.48
    ocratic
    0.47
    economic
    0.47
     légal
    0.47
     legally
    0.46
     kepem
    0.46
     socioeconomic
    0.46
    economy
    0.46
    Activations Density 0.428%

    No Known Activations