© 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. 41-GEMMASCOPE-RES-16K
    11. 10495
    Prev
    Next
    INDEX
    Explanations

    elements related to programming licenses and references in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéroïdes
    -0.46
     فريبيس
    -0.43
    最快更新
    -0.43
    vermögen
    -0.42
    ungszeit
    -0.40
    AddTagHelper
    -0.40
    writeFieldEnd
    -0.40
    läufe
    -0.39
    цездатний
    -0.39
    verhält
    -0.38
    POSITIVE LOGITS
    -
    2.80
    ‑
    1.06
    ‐
    1.05
    -​
    1.00
    ®-
    0.89
    -<
    0.89
    ־
    0.88
    -
    0.87
    -...
    0.87
    -'
    0.86
    Activations Density 10.794%

    No Known Activations