© 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 EvalsExportsinterp-engineNEWAPI 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. 4199
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding government actions and public protests

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

    expressions of strong disapproval, criticism, or moral outrage.

    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
     realistas
    -0.41
    困难
    -0.41
     Conversely
    -0.39
    Theore
    -0.39
     realista
    -0.38
     dificuldades
    -0.38
     Schwierigkeiten
    -0.38
     kesulitan
    -0.38
     :).
    -0.37
     kelebihan
    -0.37
    POSITIVE LOGITS
     shameful
    1.18
     disgraceful
    1.13
     unacceptable
    1.03
    shame
    1.03
     disgusting
    1.02
    Shame
    0.99
     shame
    0.98
     disgrace
    0.95
     appalling
    0.93
     Shame
    0.92
    Activations Density 0.556%

    No Known Activations