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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11198
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking techniques and ingredient preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isDebugEnabled
    -0.52
     estimés
    -0.48
    Chham
    -0.47
     territoire
    -0.47
    لیس
    -0.46
    getOutputStream
    -0.46
    dotto
    -0.46
     volantes
    -0.45
     mutat
    -0.45
     Ebene
    -0.44
    POSITIVE LOGITS
     overnight
    1.20
     Overnight
    0.90
    Overnight
    0.81
     soak
    0.80
     soaking
    0.77
     letting
    0.71
    存于互联网档案馆
    0.70
    vernight
    0.69
    Letting
    0.68
     Soak
    0.66
    Activations Density 0.441%

    No Known Activations