© 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. 40-GEMMASCOPE-RES-16K
    11. 5582
    Prev
    Next
    INDEX
    Explanations

    references to materials and components used in model details or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulemon
    -0.44
    Xna
    -0.42
    contentValues
    -0.38
    !*\
    -0.38
    Smarty
    -0.37
    postsleuth
    -0.37
     deslig
    -0.36
     withhold
    -0.36
     adaptive
    -0.35
    chakra
    -0.35
    POSITIVE LOGITS
     Scale
    0.92
     scale
    0.89
     modeller
    0.81
    Scale
    0.81
     kit
    0.79
     modell
    0.79
     modelling
    0.78
     kits
    0.77
    模型
    0.77
     modeling
    0.75
    Activations Density 0.143%

    No Known Activations