© 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. 103399
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols related to equations, particularly involving variables and operations

    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
    posedge
    -0.49
    AndEndTag
    -0.49
    UnusedPrivate
    -0.48
     Saeed
    -0.48
     pics
    -0.47
     Tsch
    -0.47
     peoples
    -0.45
     resourceCulture
    -0.44
     Sunglasses
    -0.44
    Mereka
    -0.44
    POSITIVE LOGITS
    }+\
    0.71
    >+</
    0.66
    }+
    0.66
    |+
    0.64
    }}+\
    0.64
    |+\
    0.62
     وتسجيلات
    0.60
    plus
    0.59
    +\
    0.54
    &+
    0.54
    Activations Density 0.317%

    No Known Activations