© 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 - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6148
    Prev
    Next
    INDEX
    Explanations

    themes of self-interest and societal issues related to morality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.95
     insofar
    -0.84
     Thereafter
    -0.83
     queſta
    -0.81
     insistent
    -0.81
     inescapable
    -0.81
     envisage
    -0.78
     totalled
    -0.78
    Personendaten
    -0.78
     foodstuffs
    -0.77
    POSITIVE LOGITS
     mode
    0.34
    theilung
    0.32
     dezelve
    0.30
     producciones
    0.29
     ​
    0.27
     zijne
    0.26
     internal
    0.25
     existing
    0.25
     deras
    0.25
     eenen
    0.25
    Activations Density 0.625%

    No Known Activations