© 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-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 5692
    Prev
    Next
    INDEX
    Explanations

    connections between neural responses and event-related language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hau
    -0.52
    Portal
    -0.48
    ChildIndex
    -0.48
     Portal
    -0.46
     sosp
    -0.46
     hini
    -0.44
    idenza
    -0.43
     ngoài
    -0.43
    cony
    -0.43
     term
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    0.86
    findpost
    0.73
     فريبيس
    0.73
    ByVersion
    0.70
     kasarigan
    0.68
     برانيه
    0.68
     trajets
    0.67
     fMRI
    0.65
     بيها
    0.64
    ılıyor
    0.64
    Activations Density 1.093%

    No Known Activations