© 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. 34-GEMMASCOPE-RES-16K
    11. 12982
    Prev
    Next
    INDEX
    Explanations

    references to Sri, indicating a focus on cultural or religious contexts, particularly related to Sri Lankan identity and significant figures or concepts in its spiritual or cultural framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.50
    AccessorTable
    -0.50
    RectangleBorder
    -0.45
    UnknownFieldSet
    -0.45
     noDo
    -0.45
     createState
    -0.44
    BufferException
    -0.44
     يتيمه
    -0.43
    jsxFileName
    -0.42
    nodoc
    -0.42
    POSITIVE LOGITS
    Sri
    0.52
    sr
    0.50
    Shr
    0.49
     Sri
    0.47
     SR
    0.47
     sr
    0.46
    vastava
    0.45
    SR
    0.44
    apimachinery
    0.43
     Srin
    0.42
    Activations Density 0.196%

    No Known Activations