Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7214
    Prev
    Next
    INDEX
    Explanations

    concepts related to the idea of divine authority and moral obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moniker
    -0.66
     transitioning
    -0.65
     upfront
    -0.64
     impactful
    -0.61
     aforementioned
    -0.61
     proactively
    -0.61
     critters
    -0.60
     upcoming
    -0.60
     timeframe
    -0.59
     anytime
    -0.58
    POSITIVE LOGITS
    SequentialGroup
    0.66
     läßt
    0.51
    UrlResolution
    0.48
     biß
    0.47
     such
    0.47
    IsContent
    0.46
    こういう
    0.46
    ้งาน
    0.45
     Miß
    0.44
     genü
    0.44
    Activations Density 1.817%

    No Known Activations