© 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. 7364
    Prev
    Next
    INDEX
    Explanations

    values associated with variable assignments and data structures

    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
    rungsseite
    -0.72
     propOrder
    -0.66
     مرئيه
    -0.58
    Rhestr
    -0.57
    CodeAttribute
    -0.56
    complexContent
    -0.56
     informée
    -0.55
     autorytatywna
    -0.55
     PeEnEo
    -0.54
     مشين
    -0.53
    POSITIVE LOGITS
     >
    0.57
     >=
    0.48
     /
    0.42
     %
    0.40
     *
    0.40
     <=
    0.40
    *-
    0.40
     dağı
    0.40
    Akhir
    0.38
     <
    0.37
    Activations Density 0.353%

    No Known Activations