© 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. 15325
    Prev
    Next
    INDEX
    Explanations

    the word "which" and its variations

    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
    lexikon
    -0.59
    @[+][
    -0.53
     pulumi
    -0.50
    timewa
    -0.50
    nyttet
    -0.50
    culate
    -0.50
    assar
    -0.49
    ZZA
    -0.48
    Gew
    -0.47
    iddhar
    -0.47
    POSITIVE LOGITS
     wiederum
    0.89
     incidentally
    0.88
     admittedly
    0.86
     unfortunately
    0.83
     кстати
    0.80
     tentunya
    0.79
     thankfully
    0.79
     itself
    0.76
     malheureusement
    0.76
     is
    0.75
    Activations Density 0.310%

    No Known Activations