© 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. 6185
    Prev
    Next
    INDEX
    Explanations

    key terms related to political power dynamics and negotiations

    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
     pervasive
    -0.32
    aura
    -0.32
     endogenous
    -0.30
     ubiquitous
    -0.30
     durer
    -0.30
     self
    -0.30
    ιά
    -0.29
    をかけ
    -0.28
     focus
    -0.28
     domestic
    -0.28
    POSITIVE LOGITS
     compensation
    1.21
     payment
    1.17
    compensation
    1.09
     repayment
    1.05
     recompense
    1.02
    payment
    1.01
    Compensation
    0.98
     Compensation
    0.96
     compens
    0.95
     payments
    0.94
    Activations Density 0.794%

    No Known Activations