© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1632
    Prev
    Next
    INDEX
    Explanations

    phrases indicating responsibility and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kyllä
    -0.39
     Mejía
    -0.37
     zupeł
    -0.36
     uitz
    -0.35
    viewtopic
    -0.35
     boletos
    -0.34
     ujednoznacz
    -0.34
     menyem
    -0.34
    quillas
    -0.34
     Grüße
    -0.33
    POSITIVE LOGITS
     responsibility
    1.67
     Responsibility
    1.63
     responsible
    1.59
     Responsible
    1.50
    responsible
    1.48
    responsibility
    1.46
    Responsible
    1.45
    Responsibility
    1.45
     responsable
    1.30
     responsabilità
    1.19
    Activations Density 0.151%

    No Known Activations