© 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. 20-GEMMASCOPE-RES-131K
    6. 12600
    Prev
    Next
    INDEX
    Explanations

    mentions of legal and financial issues, particularly regarding taxes and economic situations

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

    names, addresses, and affiliations

    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-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
    cshtml
    -0.50
     kata
    -0.43
     tak
    -0.40
     kada
    -0.40
    LabelTagHelper
    -0.40
     tag
    -0.39
     hot
    -0.38
    Beg
    -0.36
     cast
    -0.36
     Convention
    -0.36
    POSITIVE LOGITS
    ंदीखरीदारी
    0.60
    tangentMode
    0.56
    oa̍t
    0.56
    
    0.55
     estekak
    0.54
    хьтан
    0.52
     otomatig
    0.48
    bitat
    0.48
    windowFixed
    0.48
     pinulongan
    0.47
    Activations Density 0.013%

    No Known Activations