© 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. 20-GEMMASCOPE-RES-16K
    11. 11958
    Prev
    Next
    INDEX
    Explanations

    concepts related to the complexities and challenges of society

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

    references to the broader world or societal reality, especially abstract, big-picture statements about society, history, or “the real world.”

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    phrases discussing society, reality, or the state of the world in a broad, philosophical sense.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angered
    -0.58
    oa̍t
    -0.53
    Espèce
    -0.53
    liceerd
    -0.52
    culada
    -0.48
     nonUne
    -0.48
     transfieras
    -0.48
     Polda
    -0.48
     inaugurate
    -0.48
     يتيمه
    -0.47
    POSITIVE LOGITS
     world
    0.62
     mundo
    0.62
    world
    0.56
     maail
    0.52
     maailman
    0.50
     světě
    0.49
    世界
    0.48
     världen
    0.48
     světa
    0.48
     wereld
    0.47
    Activations Density 0.165%

    No Known Activations