© 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. 15-GEMMASCOPE-RES-16K
    11. 1299
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hecht
    -0.49
     Rembrandt
    -0.48
     Photographie
    -0.47
     Wachs
    -0.46
    reciated
    -0.46
     Carson
    -0.46
    +}\
    -0.46
    outstanding
    -0.45
     McPherson
    -0.44
    detach
    -0.43
    POSITIVE LOGITS
     rule
    1.73
     Rule
    1.66
    Rule
    1.62
     RULE
    1.55
     rules
    1.52
     Rules
    1.47
    rule
    1.45
    Rules
    1.41
    RULE
    1.38
     RULES
    1.34
    Activations Density 0.171%

    No Known Activations