© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 8161
    Prev
    Next
    INDEX
    Explanations

    mathematical terminology related to conformal mappings and Borel transforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xase
    -0.56
    :✨
    -0.53
     Мексичка
    -0.51
    StructEnd
    -0.51
    KindOfClass
    -0.50
    esModule
    -0.49
     ligiloj
    -0.49
    sidemargin
    -0.49
    rxjs
    -0.48
    <?
    -0.48
    POSITIVE LOGITS
     Reſ
    0.40
     pleaſure
    0.35
     poch
    0.34
    脚注の使い方
    0.33
     valida
    0.32
     conformal
    0.32
     Bessel
    0.31
     renewal
    0.30
     hyperbolic
    0.30
    Refresh
    0.30
    Activations Density 1.214%

    No Known Activations