© 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. 0-GEMMASCOPE-RES-16K
    11. 7468
    Prev
    Next
    INDEX
    Explanations

    words that indicate significant size or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Big
    -0.58
     big
    -0.55
     незавершена
    -0.54
    ային
    -0.53
    RegressionTest
    -0.52
    Composable
    -0.52
    aryen
    -0.52
    msgSender
    -0.51
    cookieParser
    -0.51
    Philly
    -0.51
    POSITIVE LOGITS
     enormous
    1.09
     immense
    1.08
     enormously
    0.94
     immensely
    0.84
    ormous
    0.76
     immen
    0.70
    mense
    0.68
     tremendously
    0.68
     tremendous
    0.66
     Peace
    0.65
    Activations Density 0.135%

    No Known Activations