© 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. 34-GEMMASCOPE-RES-16K
    11. 973
    Prev
    Next
    INDEX
    Explanations

    references to conflict or confrontation in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entusias
    -0.44
     verke
    -0.37
     acceptance
    -0.35
    Grü
    -0.35
    jakan
    -0.35
     approval
    -0.35
    💭
    -0.35
     enthusiasm
    -0.34
    zerű
    -0.34
     enthousi
    -0.32
    POSITIVE LOGITS
     retali
    0.82
     dénon
    0.73
     demand
    0.71
     ultimatum
    0.71
     threatened
    0.70
     demanded
    0.70
     demands
    0.69
     exigir
    0.66
     denunci
    0.66
    demand
    0.66
    Activations Density 0.568%

    No Known Activations