© 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. 2626
    Prev
    Next
    INDEX
    Explanations

    programming-related queries and functionalities, particularly those focused on database operations and functions in server-side scripting

    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
     koji
    -0.73
     lequel
    -0.67
     <<<<<<<<<<<<<<
    -0.65
     ktorý
    -0.65
     himself
    -0.65
     kuris
    -0.60
     који
    -0.60
     lesquels
    -0.59
     américain
    -0.56
     ones
    -0.56
    POSITIVE LOGITS
     herself
    1.23
     которая
    1.10
     która
    1.07
     která
    1.03
    herself
    1.01
     ktorá
    0.97
     която
    0.93
     которую
    0.91
     яка
    0.91
     kterou
    0.87
    Activations Density 0.201%

    No Known Activations