© 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. 3-GEMMASCOPE-RES-16K
    11. 7773
    Prev
    Next
    INDEX
    Explanations

    references to collections or groups, particularly in a scientific or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cut
    -0.80
     set
    -0.77
     run
    -0.74
     read
    -0.71
     spread
    -0.63
     cast
    -0.60
     put
    -0.58
    cut
    -0.57
     Waren
    -0.55
     Set
    -0.53
    POSITIVE LOGITS
    Sets
    1.19
     Sets
    1.13
     sets
    1.13
     SETS
    1.07
    BibitemShut
    1.06
     Perſ
    1.03
    UnusedPrivate
    1.01
     Majefty
    1.01
     Monfieur
    1.01
    bibfield
    0.99
    Activations Density 0.055%

    No Known Activations