© 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. 103743
    Prev
    Next
    INDEX
    Explanations

    terms related to conveying or communicating information

    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
    bufio
    -0.53
     esterni
    -0.52
     cartridges
    -0.50
     timers
    -0.49
     blacklist
    -0.48
    onSearch
    -0.46
     isComment
    -0.46
    kalender
    -0.46
    כשיו
    -0.45
     cartridge
    -0.45
    POSITIVE LOGITS
     conveys
    0.84
     conveyed
    0.83
     convey
    0.82
    Convey
    0.79
     conveying
    0.79
     Convey
    0.77
     transmettre
    0.69
     vermitteln
    0.66
     transmitir
    0.66
     vermittelt
    0.66
    Activations Density 0.015%

    No Known Activations