© 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. 1-GEMMASCOPE-RES-16K
    11. 7392
    Prev
    Next
    INDEX
    Explanations

    the word "wa," which is likely related to a specific subject or theme present in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Abitanti
    -0.69
    Referències
    -0.67
    wolves
    -0.64
    日閲覧
    -0.61
    ]<=
    -0.61
    ⓘ
    -0.60
    DrawerToggle
    -0.59
    ագրություններ
    -0.58
     Zorn
    -0.58
    Yours
    -0.56
    POSITIVE LOGITS
     wa
    1.02
     Wa
    0.95
    wa
    0.89
    lin
    0.88
     AssemblyCulture
    0.82
    Wa
    0.79
    WA
    0.68
     nav
    0.66
     WA
    0.66
    onAttach
    0.66
    Activations Density 0.064%

    No Known Activations