© 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. 8-GEMMASCOPE-RES-16K
    6. 5291
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and data structures in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.57
     so
    -0.51
    vi
    -0.50
     for
    -0.49
    I
    -0.49
     ви
    -0.48
    EndProject
    -0.48
     general
    -0.46
     che
    -0.46
      
    -0.45
    POSITIVE LOGITS
    <tfoot>
    0.92
     MainAxisSize
    0.84
     iſt
    0.82
     ſind
    0.80
     يتيمه
    0.76
    رشف
    0.75
     Majefty
    0.74
     doubtnut
    0.74
    RenderAtEndOf
    0.72
    AsUp
    0.70
    Activations Density 1.371%

    No Known Activations