© 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. 11-GEMMASCOPE-RES-16K
    11. 11718
    Prev
    Next
    INDEX
    Explanations

    comparative phrases differentiating subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esistenza
    -0.48
     мәкал
    -0.47
    errHandler
    -0.45
     препратки
    -0.45
    Ndr
    -0.45
    LookAnd
    -0.45
    MessageTagHelper
    -0.44
    IUrlHelper
    -0.44
    WriteLiteral
    -0.44
     дописавши
    -0.43
    POSITIVE LOGITS
     unlike
    0.86
    Unlike
    0.85
     Unlike
    0.81
    unlike
    0.81
    不像
    0.71
     отличие
    0.52
     Gegensatz
    0.47
     dissimilar
    0.43
    mimetype
    0.42
     Andersson
    0.40
    Activations Density 0.503%

    No Known Activations