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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 873
    Prev
    Next
    INDEX
    Explanations

    references to celebratory days and associated festivities

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

    "[Something]'s Day" or "Day Celebrations"

    np_acts-logits-general · gemini-2.0-flash

    holidays and days

    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
    Datuak
    -0.63
     الحره
    -0.46
     generaciones
    -0.46
     câte
    -0.45
     actualidad
    -0.45
     Italij
    -0.44
     actuación
    -0.44
    siapkan
    -0.44
    GOTREF
    -0.44
    zőkönyv
    -0.44
    POSITIVE LOGITS
     Preview
    0.44
    TargetException
    0.44
     Halloween
    0.44
    titleMargin
    0.43
    InstrumentedTest
    0.43
     Weekend
    0.42
     tec
    0.42
     onCreateView
    0.42
    Authors
    0.42
    URLException
    0.41
    Activations Density 0.211%

    No Known Activations