© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4031
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency and effectiveness

    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
    openqa
    -0.74
    reactstrap
    -0.69
    Diwedd
    -0.67
    brooks
    -0.67
    Personensuche
    -0.65
    llten
    -0.65
     subjek
    -0.63
    quelize
    -0.62
     pastors
    -0.62
     Blackstone
    -0.62
    POSITIVE LOGITS
     efficient
    3.14
    efficient
    2.96
     Efficient
    2.87
     efficiency
    2.74
    Efficient
    2.74
     efficiently
    2.51
     Efficiency
    2.48
    efficiency
    2.41
    Efficiency
    2.40
     efficiencies
    2.31
    Activations Density 0.069%

    No Known Activations