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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-131K
    11. 99975
    Prev
    Next
    INDEX
    Explanations

    elements related to rebellion, criticism, and defense of ideological positions

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

    defend, uphold, protect

    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
     Rango
    -0.39
    Jîn
    -0.38
    handlebars
    -0.34
     pector
    -0.32
     اث
    -0.32
    Terrain
    -0.32
     papilla
    -0.32
     JTextArea
    -0.31
    etcode
    -0.31
    scriptcase
    -0.31
    POSITIVE LOGITS
    basicConfig
    0.57
     Comprometido
    0.56
    Портали
    0.52
    fromCharCode
    0.48
     الحره
    0.45
     integrados
    0.44
     rescate
    0.44
     AssemblyProduct
    0.44
     cerrados
    0.44
     integración
    0.43
    Activations Density 0.132%

    No Known Activations