© 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. 2-GEMMASCOPE-RES-16K
    6. 13815
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "code" related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Keuangan
    -0.40
     daarvan
    -0.40
     biologique
    -0.38
    complexContent
    -0.37
     vâ
    -0.36
     llorando
    -0.35
     Bewußt
    -0.35
     végétale
    -0.35
    [++
    -0.34
     extérieure
    -0.34
    POSITIVE LOGITS
    code
    1.04
    codes
    0.63
    hash
    0.60
     hash
    0.58
     Hash
    0.57
     science
    0.56
     Science
    0.54
     Scoop
    0.54
    science
    0.52
     ya
    0.52
    Activations Density 0.139%

    No Known Activations