Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 94999
    Prev
    Next
    INDEX
    Explanations

    references to sunsets and their variations

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

    sunset and dusk

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     للمعارف
    -0.47
    a
    -0.45
    maßen
    -0.42
    NameInMap
    -0.39
    ians
    -0.39
     Joao
    -0.38
     rzeczy
    -0.37
    Iain
    -0.37
    mitglieder
    -0.36
    äure
    -0.36
    POSITIVE LOGITS
     Sunset
    1.30
    Sunset
    1.28
     sunset
    1.20
    sunset
    1.14
     sunsets
    0.95
     tramonto
    0.82
     atardecer
    0.77
    ardecer
    0.73
    twilight
    0.73
     sundown
    0.72
    Activations Density 0.001%

    No Known Activations