© 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. 19-GEMMASCOPE-RES-16K
    11. 5125
    Prev
    Next
    INDEX
    Explanations

    sequences and their related concepts in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !("{
    -0.71
    ########.
    -0.68
    felves
    -0.67
     Efq
    -0.67
    rawDesc
    -0.66
     embers
    -0.66
    IsPostBack
    -0.65
    Портал
    -0.64
    ſelf
    -0.64
    MessageTagHelper
    -0.63
    POSITIVE LOGITS
     sequences
    1.39
     seq
    1.38
     Sequences
    1.26
     Sequence
    1.24
     sequence
    1.22
     SEQUENCE
    1.16
    Sequences
    1.15
     sequ
    1.13
    Sequence
    1.11
     Sequ
    1.09
    Activations Density 0.155%

    No Known Activations