© 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. 13-GEMMASCOPE-RES-16K
    11. 13662
    Prev
    Next
    INDEX
    Explanations

    terminology related to statistics and semiconductor properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.55
     насељу
    -0.52
    <eos>
    -0.51
     Pre
    -0.51
     дописавши
    -0.50
     bezeichneter
    -0.48
    存于互联网档案馆
    -0.47
    UNIDENTIFIED
    -0.46
    ']}
    -0.46
     https
    -0.46
    POSITIVE LOGITS
     houſe
    0.93
     ſtate
    0.93
     Efq
    0.92
    ”—
    0.90
     Jefus
    0.90
     Majefty
    0.89
     Reſ
    0.88
     Houſe
    0.87
     pleaſure
    0.86
     greateſt
    0.86
    Activations Density 0.697%

    No Known Activations