© 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. 14-GEMMASCOPE-RES-16K
    11. 8779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating authority and hierarchical structures within belief systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.60
    queryInterface
    -0.58
    UnusedPrivate
    -0.48
     Jefus
    -0.47
    หวัด
    -0.47
     ſever
    -0.47
     ſeveral
    -0.45
    NameInMap
    -0.45
    ſelves
    -0.44
    Microkernel
    -0.44
    POSITIVE LOGITS
    authority
    0.60
    权威
    0.52
     authority
    0.51
     Authority
    0.45
     authoritative
    0.45
    Authority
    0.43
     karar
    0.43
     instructions
    0.43
    instructions
    0.42
     lời
    0.41
    Activations Density 0.496%

    No Known Activations