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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8624
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding the influence of beliefs and values on society and governance

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

    "society" and related concepts

    np_acts-logits-general · gemini-2.0-flash

    society and population

    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
     Audiodateien
    -0.53
    onActivityResult
    -0.53
    期刊论文
    -0.52
    OrNil
    -0.51
     MainAxisSize
    -0.50
    jectures
    -0.49
    WebElementEntity
    -0.48
    もしれません
    -0.48
    Datuak
    -0.48
    eapples
    -0.48
    POSITIVE LOGITS
     society
    1.50
    society
    1.17
     sociedad
    1.15
     sociedade
    1.09
     societies
    1.05
     общества
    0.98
     SOCIETY
    0.96
     masyarakat
    0.94
     общество
    0.91
     sociedades
    0.90
    Activations Density 0.357%

    No Known Activations