© 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. 9-GEMMASCOPE-RES-16K
    11. 2243
    Prev
    Next
    INDEX
    Explanations

    the letter "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     investi
    -0.83
     indepen
    -0.77
     vig
    -0.77
     exces
    -0.76
     equili
    -0.76
     esper
    -0.75
     enthusi
    -0.75
     conci
    -0.72
     Venkates
    -0.72
     opis
    -0.72
    POSITIVE LOGITS
    A
    1.36
    getA
    1.23
     A
    1.16
    a
    0.98
    aA
    0.97
     aarde
    0.86
     a
    0.86
    bA
    0.85
     fenomeno
    0.84
     brancas
    0.84
    Activations Density 0.461%

    No Known Activations