© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8258
    Prev
    Next
    INDEX
    Explanations

    concepts related to socio-political dynamics and frameworks of power

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

    abstract academic and social-theory discourse, especially dense jargon about power structures, identity, race, history, and information/interaction processes

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    academic or scholarly discussions about social sciences, particularly those analyzing cultural, historical, or sociological topics and their intersections.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyCulture
    -0.64
     ProtoMessage
    -0.63
    StoryboardSegue
    -0.60
     الرياضيه
    -0.56
     intptr
    -0.52
     Infórmanos
    -0.51
     autorytatywna
    -0.50
    complexContent
    -0.49
     CreateTagHelper
    -0.49
     propOrder
    -0.48
    POSITIVE LOGITS
     narratives
    0.53
     participatory
    0.51
     sensibilities
    0.51
     transformative
    0.51
     contexts
    0.50
     spaces
    0.49
     spatio
    0.49
     collective
    0.49
     discourse
    0.49
     cultural
    0.48
    Activations Density 0.201%

    No Known Activations