© 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. 40-GEMMASCOPE-RES-16K
    11. 5570
    Prev
    Next
    INDEX
    Explanations

    phrases indicating moral responsibility and societal critique regarding historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     човек
    -0.59
    someone
    -0.53
     someone
    -0.53
     navideñas
    -0.52
     person
    -0.51
    這位
    -0.50
     cortas
    -0.48
     Someone
    -0.48
     Seorang
    -0.48
     cielos
    -0.47
    POSITIVE LOGITS
     innovators
    1.39
     pioneers
    1.37
     winners
    1.35
     heroes
    1.27
     champions
    1.27
     creators
    1.27
     liars
    1.27
     professionals
    1.26
     leaders
    1.25
     experts
    1.25
    Activations Density 1.296%

    No Known Activations