© 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. 27-GEMMASCOPE-RES-16K
    11. 10032
    Prev
    Next
    INDEX
    Explanations

    themes of sacrifice and protection in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.51
     NSCoder
    -0.50
    RegistryLite
    -0.50
    endpush
    -0.49
    ChildScrollView
    -0.48
     незавершена
    -0.47
     consultato
    -0.45
     autorytatywna
    -0.44
     cree
    -0.43
     ujednoznacz
    -0.43
    POSITIVE LOGITS
     sacrifice
    1.31
     sacrificial
    1.26
     sacrificing
    1.22
     sacrificed
    1.20
     sacrifices
    1.14
     sacrific
    1.13
    sacrific
    1.13
     Sacrific
    1.06
     sacrificio
    1.03
     selfless
    1.02
    Activations Density 0.243%

    No Known Activations