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. 8945
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to energy efficiency and power consumption

    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
     propOrder
    -0.63
    URLException
    -0.61
    guten
    -0.52
     protoimpl
    -0.50
    Personendaten
    -0.50
    JspWriter
    -0.49
     betweenstory
    -0.49
     comuniques
    -0.49
    cista
    -0.48
     intonation
    -0.48
    POSITIVE LOGITS
     consumption
    2.21
     consume
    1.98
     Consumption
    1.95
    consumption
    1.91
     consuming
    1.90
     consumed
    1.88
     consumes
    1.84
    Consumption
    1.79
     CONSUM
    1.69
     consumo
    1.66
    Activations Density 0.391%

    No Known Activations