© 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. 3-GEMMASCOPE-RES-16K
    11. 6635
    Prev
    Next
    INDEX
    Explanations

    phrases associated with effectiveness and accuracy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.72
    jago
    -0.67
    InitVars
    -0.64
    IntoConstraints
    -0.63
     kasarigan
    -0.62
     Roskov
    -0.62
    usda
    -0.62
    cyklopedia
    -0.61
    enumi
    -0.60
    Personensuche
    -0.59
    POSITIVE LOGITS
     reliability
    0.94
     performance
    0.88
     efficiency
    0.84
     efficacy
    0.83
     accuracy
    0.83
    performance
    0.81
     effectiveness
    0.79
    efficacité
    0.76
    efficiency
    0.76
     trustworthiness
    0.75
    Activations Density 0.761%

    No Known Activations