© 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. 21-GEMMASCOPE-RES-16K
    11. 12018
    Prev
    Next
    INDEX
    Explanations

    mentions of different groups or categories within a study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ︎
    -0.74
     Wund
    -0.69
    Архівовано
    -0.67
     Krie
    -0.63
    enumi
    -0.61
    csolódó
    -0.58
    !("{}",
    -0.57
     ModelExpression
    -0.55
    ]-->
    -0.55
    reportWebVitals
    -0.55
    POSITIVE LOGITS
     getGroup
    1.17
     groups
    1.15
     Groups
    1.05
    groups
    0.95
    Groups
    0.89
     group
    0.89
     GROUPS
    0.84
     Gruppen
    0.80
     Group
    0.77
     GROUP
    0.77
    Activations Density 0.167%

    No Known Activations