© 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. 31-GEMMASCOPE-RES-16K
    11. 10841
    Prev
    Next
    INDEX
    Explanations

    discussions around political and social narratives related to race and identity

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

    statements that make hypocritical or contradictory accusations against political opponents.

    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
     consape
    -0.47
     hué
    -0.45
     zdecydow
    -0.44
     IMHO
    -0.43
    可以说
    -0.43
     IMO
    -0.42
    tershire
    -0.42
    يميديا
    -0.42
     menyadari
    -0.41
     riconos
    -0.41
    POSITIVE LOGITS
     somehow
    0.98
     яко
    0.79
     magically
    0.78
     supposedly
    0.70
     Somehow
    0.62
     angeb
    0.61
     superior
    0.60
    Somehow
    0.58
    Portály
    0.57
     miraculously
    0.57
    Activations Density 1.127%

    No Known Activations