© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1654
    Prev
    Next
    INDEX
    Explanations

    logical relationships and mathematical structures in the context of set theory and graph theory

    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
     propOrder
    -0.96
     transfieras
    -0.78
    EndContext
    -0.78
     AssemblyCulture
    -0.75
     kasarigan
    -0.75
     NSCoder
    -0.75
    ftagPool
    -0.72
    verifyException
    -0.71
    Tikang
    -0.70
     Geiſt
    -0.70
    POSITIVE LOGITS
     (
    0.56
    (
    0.39
     användas
    0.34
    のでしょうか
    0.34
     Jurí
    0.28
    ?
    0.27
     polskiego
    0.27
    MockBean
    0.27
    érable
    0.26
    期刊论文
    0.26
    Activations Density 0.966%

    No Known Activations