© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14036
    Prev
    Next
    INDEX
    Explanations

    quantities or references to varying amounts of subjects, including the term "some" in diverse contexts

    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
     of
    -0.58
     hoort
    -0.58
    thâu
    -0.54
    ใคร
    -0.53
    狙
    -0.53
     Glaser
    -0.50
     who
    -0.50
    อนไลน์
    -0.48
    1
    -0.48
    卓
    -0.48
    POSITIVE LOGITS
    CloseOperation
    1.02
    resizingMask
    0.84
    //</
    0.82
     endroits
    0.76
    PreferredItem
    0.73
     odkazy
    0.73
     pinulongan
    0.72
     Nesse
    0.71
    cesis
    0.70
    BagConstraints
    0.70
    Activations Density 0.311%

    No Known Activations