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

    Neuronpedia

    Jacobian LensNEW
    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. 1770
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and logical operators

    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
    StoryboardSegue
    -0.77
    脚注の使い方
    -0.75
    Zeneca
    -0.70
     jsPsych
    -0.68
     للاسماء
    -0.66
    devamını
    -0.65
     kasarigan
    -0.65
     adjoint
    -0.65
    Referanser
    -0.63
    :+:
    -0.62
    POSITIVE LOGITS
     throughout
    0.61
    istoitu
    0.60
    forall
    0.52
    throughout
    0.52
     ACROSS
    0.51
     xét
    0.49
     quanh
    0.49
     across
    0.48
     gedurende
    0.48
     regardless
    0.48
    Activations Density 0.493%

    No Known Activations