© 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 EvalsExportsAPI 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. 1285
    Prev
    Next
    INDEX
    Explanations

    words denoting strong emotions or qualities related to enthusiasm and unexpectedness

    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
    writeFieldEnd
    -0.57
    ngdoc
    -0.54
    rungsseite
    -0.54
    ModelSerializer
    -0.52
     atlik
    -0.51
     resourceCulture
    -0.51
    jší
    -0.49
     Infórmanos
    -0.49
     &___
    -0.49
    Бахар
    -0.48
    POSITIVE LOGITS
    ly
    1.72
    ally
    1.47
    ingly
    1.43
    ably
    1.37
    ually
    1.34
    ically
    1.34
    LY
    1.31
    fully
    1.29
    atively
    1.28
    ently
    1.27
    Activations Density 0.567%

    No Known Activations