© 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. 4282
    Prev
    Next
    INDEX
    Explanations

    social interactions and gatherings

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

    associated with gatherings or events

    np_acts-logits-general · gemini-2.0-flash

    social gatherings, events, and meeting places

    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
    ftagPool
    -0.57
    ViewImports
    -0.50
    InjectAttribute
    -0.47
    存于互联网档案馆
    -0.47
    MathML
    -0.44
     fédé
    -0.44
    Наводи
    -0.43
     apparaissent
    -0.42
     anuales
    -0.42
     evolucion
    -0.42
    POSITIVE LOGITS
    shuffle
    0.45
    Aktualisiert
    0.45
    webElementXpaths
    0.43
     DevComponents
    0.40
     indisponible
    0.40
    onOptions
    0.39
     fratern
    0.38
    Personendaten
    0.36
     fluorine
    0.36
    izontal
    0.35
    Activations Density 0.166%

    No Known Activations