© 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. 9-GEMMASCOPE-RES-16K
    11. 1957
    Prev
    Next
    INDEX
    Explanations

    concepts related to coding structures and modular programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.99
     Савезне
    -0.81
    parsedMessage
    -0.78
    üyada
    -0.76
    ,:,
    -0.72
    tagext
    -0.71
    atisk
    -0.71
    PerformLayout
    -0.70
    Портали
    -0.69
    :✨
    -0.69
    POSITIVE LOGITS
    Przypisy
    0.75
     NSCoder
    0.57
    ciaż
    0.57
    URLException
    0.53
    Weblinks
    0.52
     popoli
    0.51
     decorativa
    0.51
     AssemblyVersion
    0.51
     financeira
    0.49
     ospiti
    0.49
    Activations Density 0.610%

    No Known Activations