© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9138
    Prev
    Next
    INDEX
    Explanations

    references to power dynamics and hierarchical oppression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "power" or wielding power

    np_acts-logits-general · gemini-2.0-flash

    power and authority

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.46
     ModelExpression
    -0.44
     χρό
    -0.44
     istrinya
    -0.43
     lauf
    -0.42
    BibitemShut
    -0.42
     varandra
    -0.40
     Nachbar
    -0.40
     gorą
    -0.39
     Abandon
    -0.39
    POSITIVE LOGITS
     power
    1.35
    power
    1.16
     authority
    1.01
    Power
    0.99
     Power
    0.94
     POWER
    0.93
     Macht
    0.89
    POWER
    0.87
     dominance
    0.85
     poder
    0.85
    Activations Density 0.493%

    No Known Activations