© 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. 33-GEMMASCOPE-RES-16K
    11. 11249
    Prev
    Next
    INDEX
    Explanations

    sections or statements that emphasize significant changes or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.72
    awtextra
    -0.67
     pinulongan
    -0.61
     nahilalakip
    -0.61
    XmlAccessorType
    -0.59
    ErrUnexpectedEOF
    -0.58
    
    -0.58
    msgTypes
    -0.57
    neurial
    -0.56
    astify
    -0.56
    POSITIVE LOGITS
     vandens
    0.29
     canst
    0.29
    FromNib
    0.28
    füh
    0.27
     auprès
    0.26
    čiau
    0.26
    rrggbb
    0.26
     szolg
    0.25
     państw
    0.25
     leopardo
    0.25
    Activations Density 0.762%

    No Known Activations