© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 7297
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions that pose questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
    lepiej
    -0.70
    بوابة
    -0.68
     poitrine
    -0.66
     grève
    -0.66
     gloire
    -0.62
    BorderLayout
    -0.62
    Polecam
    -0.62
     poignée
    -0.62
    Metode
    -0.61
     versioni
    -0.61
    POSITIVE LOGITS
     question
    4.01
     questions
    3.48
     Question
    3.44
    question
    3.38
    Question
    3.12
     QUESTION
    3.08
     Questions
    2.96
    questions
    2.90
    Questions
    2.81
     Frage
    2.66
    Activations Density 0.073%

    No Known Activations