© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11422
    Prev
    Next
    INDEX
    Explanations

    questions and phrases that seek clarification or identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SafeMath
    -0.70
    uxley
    -0.62
     = 
    -0.61
    ])).
    -0.60
     Familienname
    -0.59
    toolbox
    -0.58
    remoto
    -0.56
    ngdoc
    -0.55
     Foxx
    -0.55
    loroethane
    -0.55
    POSITIVE LOGITS
     distinguish
    0.80
     distinguishing
    0.78
     discerned
    0.76
     Unterscheidung
    0.74
     distinguir
    0.72
     discern
    0.72
     distinguer
    0.72
     tell
    0.70
     discer
    0.70
    distingu
    0.70
    Activations Density 0.471%

    No Known Activations