© 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. 38-GEMMASCOPE-RES-16K
    11. 11098
    Prev
    Next
    INDEX
    Explanations

    references to political dynamics and situations involving power struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     témoins
    -0.39
     Verantwort
    -0.35
     richied
    -0.35
     rhestr
    -0.35
     Worte
    -0.35
     ricor
    -0.34
     amateurs
    -0.34
     nuages
    -0.34
     MediatR
    -0.33
    앗
    -0.33
    POSITIVE LOGITS
     aligning
    1.16
     loyalty
    1.16
     allegiance
    1.15
     aligned
    1.10
     loyal
    1.06
     align
    1.05
     alignment
    1.04
     siding
    1.00
     loy
    0.98
     aligns
    0.96
    Activations Density 1.160%

    No Known Activations