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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16209
    Prev
    Next
    INDEX
    Explanations

    references to authors, books, and literary awards in Australian literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sweeney
    -0.91
     CreateTagHelper
    -0.88
    くい
    -0.82
    o
    -0.77
     Meri
    -0.75
     MRP
    -0.75
     Fass
    -0.73
     Mous
    -0.71
     Burroughs
    -0.71
    LEADING
    -0.68
    POSITIVE LOGITS
    ly
    1.47
    جوايز
    1.06
    OfBirth
    0.94
     Hust
    0.92
     Ulla
    0.89
     TimeUnit
    0.89
     חיצוניים
    0.86
     bross
    0.86
     Krug
    0.86
    mente
    0.86
    Activations Density 13.193%

    No Known Activations