© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    references to testimony and the act of testifying in legal contexts

    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
    :\/\/
    -0.81
     StringTokenizer
    -0.76
     Klas
    -0.73
     Eta
    -0.72
    ANTLR
    -0.72
     ligiloj
    -0.71
    endpush
    -0.71
     OMITBAD
    -0.70
     nakalista
    -0.70
    NameInMap
    -0.70
    POSITIVE LOGITS
     testimony
    1.51
     testify
    1.39
    testi
    1.34
     Testimony
    1.34
    Testi
    1.29
     testimonies
    1.27
     testified
    1.25
     testifies
    1.14
     testifying
    1.10
     testimonio
    1.06
    Activations Density 0.111%

    No Known Activations