© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6644
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or endorsement in discussions

    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
    AnimationsModule
    -0.48
     Gamb
    -0.39
     isInitialized
    -0.38
     invokingState
    -0.37
     استنادى
    -0.36
     defaultstate
    -0.36
    ChildIndex
    -0.36
    出版年
    -0.36
    ")));
    
    -0.35
    Спасылкі
    -0.35
    POSITIVE LOGITS
     agree
    2.77
     agrees
    2.50
     Agree
    2.34
     agreeing
    2.31
    agree
    2.28
     agreed
    2.25
    Agree
    2.25
     agreement
    2.11
     Agreed
    2.02
    agreed
    2.00
    Activations Density 0.699%

    No Known Activations