© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 2846
    Prev
    Next
    INDEX
    Explanations

    references to the concept of consumption, particularly in relation to dietary and resource usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.74
     atof
    -0.68
    اضي
    -0.67
     Yarm
    -0.64
     maxn
    -0.63
     sonora
    -0.62
     Nite
    -0.61
    rätt
    -0.60
     ureter
    -0.59
     plads
    -0.59
    POSITIVE LOGITS
     consumption
    3.10
     Consumption
    2.91
     consume
    2.77
    consumption
    2.72
    Consumption
    2.65
     consuming
    2.54
     consumed
    2.52
     Consume
    2.42
     consumes
    2.34
     CONSUM
    2.24
    Activations Density 0.070%

    No Known Activations