© 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. 12-GEMMASCOPE-RES-16K
    11. 205
    Prev
    Next
    INDEX
    Explanations

    scientific terms and entities related to research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -1.01
    {#
    -0.80
     &___
    -0.79
     Exact
    -0.76
    setVerticalGroup
    -0.73
    prepareStatement
    -0.73
    PRNewswire
    -0.72
    createStatement
    -0.71
    팎
    -0.66
    SUBJECT
    -0.65
    POSITIVE LOGITS
     Lohan
    1.02
     LS
    0.94
     Ls
    0.91
    esgue
    0.91
     LF
    0.87
     LK
    0.85
     L
    0.83
     LCS
    0.83
     LU
    0.81
     LH
    0.80
    Activations Density 1.270%

    No Known Activations