© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 492
    Prev
    Next
    INDEX
    Explanations

    phrases indicating collective action or team dynamics

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

    "We are/were" statements

    np_acts-logits-general · gemini-2.0-flash

    we are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     Widerspruch
    -0.36
     itself
    -0.35
     monasterio
    -0.35
     maternidade
    -0.33
     Moyen
    -0.32
    tiéndose
    -0.32
     Finlande
    -0.32
     Japão
    -0.31
     producteur
    -0.31
     besos
    -0.31
    POSITIVE LOGITS
    хьтан
    0.63
     Administrativna
    0.57
     We
    0.56
     ProtoMessage
    0.56
    elfare
    0.56
    thâu
    0.56
    ourite
    0.54
    nail
    0.53
     Arrange
    0.53
    JvmStatic
    0.53
    Activations Density 0.358%

    No Known Activations