© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 41-GEMMASCOPE-RES-16K
    11. 7159
    Prev
    Next
    INDEX
    Explanations

    references to benefits and advantages in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.53
    prepareStatement
    -0.47
    PostInfinity
    -0.43
     зада
    -0.42
    Probl
    -0.40
    Problema
    -0.40
     glück
    -0.38
    PCell
    -0.38
     gelukkig
    -0.37
     requisito
    -0.37
    POSITIVE LOGITS
     accrue
    1.01
     accruing
    0.99
     accrued
    0.96
     gained
    0.96
     accru
    0.89
     afforded
    0.81
     enjoyed
    0.81
     derived
    0.80
     conferred
    0.80
     outweigh
    0.79
    Activations Density 0.597%

    No Known Activations