© 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. 34-GEMMASCOPE-RES-16K
    11. 10851
    Prev
    Next
    INDEX
    Explanations

    programming-related language constructs and syntactical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insuffisamment
    -0.49
     disponibilités
    -0.47
     Wiktionnaire
    -0.45
    sonaro
    -0.42
     يتيمه
    -0.42
     bureaux
    -0.40
    httphttps
    -0.40
    ⟬
    -0.39
     ffilmiau
    -0.38
    ſelves
    -0.38
    POSITIVE LOGITS
     get
    0.69
     execute
    0.66
     run
    0.66
     go
    0.64
     start
    0.61
     perform
    0.60
     show
    0.60
     exec
    0.59
     do
    0.58
     give
    0.57
    Activations Density 0.130%

    No Known Activations