© 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. 23-GEMMASCOPE-RES-16K
    11. 9600
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to assessments or evaluations, particularly in the context of trading and market comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     schnelle
    -0.52
     kleinere
    -0.49
     ältere
    -0.48
     weißen
    -0.47
     weißem
    -0.47
     einzige
    -0.47
     profundos
    -0.46
     weiße
    -0.45
     größere
    -0.44
     supposed
    -0.44
    POSITIVE LOGITS
     AssemblyTitle
    0.77
     مشين
    0.76
    XmlAccessType
    0.73
    HostException
    0.73
    참고
    0.73
    MLLoader
    0.73
     שוליים
    0.73
    RegressionTest
    0.72
    AccessorTable
    0.72
    Vidite
    0.69
    Activations Density 0.045%

    No Known Activations