© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35618
    Prev
    Next
    INDEX
    Explanations

    phrases that resemble quoted text or quotations in legal contexts

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

    quote start and end punctuation

    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
    SharedCtor
    -0.67
    новништво
    -0.62
     initComponents
    -0.59
    Abitanti
    -0.59
    AccessorTable
    -0.58
     Photocase
    -0.57
    oredCriteria
    -0.57
    السكان
    -0.55
     Infórmanos
    -0.55
    Datuak
    -0.54
    POSITIVE LOGITS
     litté
    0.32
    estens
    0.31
     Zain
    0.31
    ftagPool
    0.30
     dė
    0.30
     särsk
    0.29
    NOPQRST
    0.28
    estimators
    0.28
     šķ
    0.28
     tør
    0.28
    Activations Density 0.036%

    No Known Activations