© 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. 27-GEMMASCOPE-RES-16K
    11. 11707
    Prev
    Next
    INDEX
    Explanations

    discussions about future plans and aspirations, particularly relating to vision and direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.69
    хьтан
    -0.68
     للاسماء
    -0.56
    ImageContext
    -0.56
    ⟬
    -0.54
     <>",
    -0.51
    erçe
    -0.51
    IUrlHelper
    -0.48
    featureID
    -0.48
    ufact
    -0.47
    POSITIVE LOGITS
     future
    2.00
    future
    1.75
    Future
    1.54
     futuro
    1.48
     FUTURE
    1.44
     toekomst
    1.44
     Future
    1.43
     Zukunft
    1.41
    FUTURE
    1.40
    未来
    1.34
    Activations Density 0.264%

    No Known Activations