© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3284
    Prev
    Next
    INDEX
    Explanations

    phrases related to social systems and cultural dynamics

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

    scholarly and academic writing about historical, social, and cultural analysis.

    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
     beauty
    -0.48
     AssemblyCulture
    -0.48
    :✨
    -0.46
     beautiful
    -0.45
    beauty
    -0.43
     someday
    -0.42
    beautiful
    -0.42
     Philosopher
    -0.41
     beginnetje
    -0.40
     atualmente
    -0.40
    POSITIVE LOGITS
     institucional
    0.57
     transnational
    0.54
     postwar
    0.54
    ThroughAttribute
    0.53
    offsetof
    0.52
    TypedDataSet
    0.52
     temprano
    0.52
    makeText
    0.52
     прежде
    0.50
    RegistryLite
    0.50
    Activations Density 0.823%

    No Known Activations