© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11186
    Prev
    Next
    INDEX
    Explanations

    references to compliance with safety and regulatory standards

    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
    
    -0.39
     <<<<<<<<<<<<<<
    -0.39
    intéress
    -0.39
     tavo
    -0.37
    varlak
    -0.37
     telefónica
    -0.36
     استنادى
    -0.36
     monnaie
    -0.36
     колек
    -0.36
     solitario
    -0.36
    POSITIVE LOGITS
     compliance
    1.22
     compliant
    1.12
     Compliance
    1.09
     comply
    1.09
     certification
    1.09
     complies
    1.08
    Compliance
    1.05
     certifications
    1.04
    compliance
    1.02
     conformity
    1.01
    Activations Density 0.253%

    No Known Activations