© 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. 14-GEMMASCOPE-RES-16K
    11. 685
    Prev
    Next
    INDEX
    Explanations

    themes related to research coordination and standardization in scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.71
     стаття
    -0.54
    NewUrlParser
    -0.53
    figcaption
    -0.52
    tagHelperRunner
    -0.51
     שוליים
    -0.50
    jspx
    -0.49
    ExtendWith
    -0.48
    estad
    -0.48
    ArgsConstructor
    -0.47
    POSITIVE LOGITS
     unified
    1.03
     uniformity
    1.02
    統一
    1.02
     einheit
    0.99
     Consistency
    0.95
     consistency
    0.95
     uniform
    0.93
     unifying
    0.91
     Uniform
    0.89
     unify
    0.89
    Activations Density 0.377%

    No Known Activations