© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103535
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific concepts and technologies, particularly in the fields of physics and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     miniaturka
    -0.76
     <<<<<<<<<<<<<<
    -0.73
    RenderAtEndOf
    -0.68
     desmotivaciones
    -0.66
     ilustracja
    -0.66
     Vereinbarung
    -0.65
     pegatina
    -0.63
     varandra
    -0.62
     Infór
    -0.60
     الحره
    -0.60
    POSITIVE LOGITS
     artific
    0.43
    ScopeManager
    0.35
     alls
    0.33
    页面存档备份
    0.33
     abra
    0.33
     arab
    0.33
     Auto
    0.31
    RTLD
    0.31
     English
    0.30
     rv
    0.30
    Activations Density 0.180%

    No Known Activations