© 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. 15-GEMMASCOPE-RES-16K
    11. 719
    Prev
    Next
    INDEX
    Explanations

    references to discussions or analyses that will be elaborated on later in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.56
    flashdata
    -0.55
     références
    -0.52
    Cyfarwyddwr
    -0.51
     gynhyrchwyd
    -0.49
    featureID
    -0.49
    saraba
    -0.49
    ftagPool
    -0.49
    XmlAccessType
    -0.48
    الحياه
    -0.47
    POSITIVE LOGITS
     later
    1.31
    later
    1.04
     senere
    1.02
    Later
    0.97
    RenderAtEndOf
    0.96
     next
    0.94
     subsequent
    0.91
     Later
    0.91
     später
    0.91
     hereinafter
    0.90
    Activations Density 0.567%

    No Known Activations