© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104416
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to mathematical or statistical frameworks

    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
    NameInMap
    -0.81
    WebVitals
    -0.76
     AssemblyCulture
    -0.68
    存于互联网档案馆
    -0.66
    enumii
    -0.63
    httphttps
    -0.63
    NUMX
    -0.62
    jsxFileName
    -0.61
    GOTREF
    -0.59
    StoryboardSegue
    -0.58
    POSITIVE LOGITS
     typically
    0.54
     famously
    0.53
     traditionally
    0.46
     commonly
    0.46
    typically
    0.44
     notoriously
    0.43
     originally
    0.42
     usually
    0.42
    ⓧ
    0.42
     gewöhnlich
    0.40
    Activations Density 0.303%

    No Known Activations