© 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. 9-GEMMASCOPE-RES-16K
    11. 7486
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to category theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.66
     defaultstate
    -0.61
     <=",
    -0.53
    حوالہ
    -0.52
    뀐
    -0.52
    новниш
    -0.50
     Blacklist
    -0.50
    Бахар
    -0.50
     unregistered
    -0.49
    Personensuche
    -0.48
    POSITIVE LOGITS
    Composable
    0.41
     práctico
    0.36
    Geplaatst
    0.35
     Kette
    0.35
     Réponses
    0.34
    IBase
    0.34
    StackNavigator
    0.33
    ViewById
    0.32
    /***/
    0.32
    kning
    0.31
    Activations Density 1.286%

    No Known Activations