© 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. 3807
    Prev
    Next
    INDEX
    Explanations

    header or introductory markers indicating a beginning of a new section or topic

    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
     
    -0.66
     supposedly
    -0.66
    <eos>
    -0.63
     clunky
    -0.61
     desperation
    -0.59
    UI
    -0.57
     clueless
    -0.56
     A
    -0.56
     supposed
    -0.56
     exactly
    -0.55
    POSITIVE LOGITS
     itſelf
    1.24
     myſelf
    1.22
    ſelf
    1.19
     pleaſure
    1.12
    ſelves
    1.12
     auffi
    1.11
     purpoſe
    1.10
     Efq
    1.08
     ſtate
    1.05
     cauſe
    1.04
    Activations Density 0.304%

    No Known Activations