© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 14031
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of being 'on' or 'upon'

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

    the phrase "on the" followed by a noun or adjective.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.65
     AssemblyCulture
    -0.62
    Diweddarwch
    -0.61
    ViewFeatures
    -0.60
    AnchorStyles
    -0.56
    SourceChecksum
    -0.55
    wieś
    -0.55
    Rüyada
    -0.52
    ContentAsync
    -0.51
    évaluateur
    -0.50
    POSITIVE LOGITS
     verge
    0.52
     mission
    0.50
     precipice
    0.50
     probation
    0.49
     alert
    0.47
     lookout
    0.45
     crutches
    0.45
     cusp
    0.45
     parole
    0.45
     footing
    0.45
    Activations Density 0.143%

    No Known Activations