© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 16120
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or expressions relating to value and worth

    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
    而是
    -0.54
     instead
    -0.53
    tsin
    -0.53
     Instead
    -0.52
     lại
    -0.52
    Instead
    -0.51
    eningen
    -0.48
     statt
    -0.48
    )();
    -0.48
    ())));
    -0.47
    POSITIVE LOGITS
     nothing
    2.56
    nothing
    2.30
    Nothing
    2.10
     Nothing
    2.08
     NOTHING
    1.99
     nowhere
    1.79
    NOTHING
    1.79
     nobody
    1.77
     nessun
    1.76
     nothin
    1.68
    Activations Density 0.223%

    No Known Activations