© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 803
    Prev
    Next
    INDEX
    Explanations

    occurrences related to lighting and candles, often in the context of celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shower
    -0.46
     só
    -0.45
    仁
    -0.44
    roba
    -0.44
    Ộ
    -0.44
    cheibe
    -0.43
    饋
    -0.43
    fieldId
    -0.43
    cipar
    -0.43
    Gep
    -0.42
    POSITIVE LOGITS
     candles
    1.38
     Candles
    1.30
     candle
    1.27
    Candles
    1.26
     Candle
    1.18
    Candle
    1.17
    candle
    1.14
    candles
    1.06
    Extinguishing
    0.95
     extinguishing
    0.94
    Activations Density 0.168%

    No Known Activations