© 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. 11-GEMMASCOPE-RES-16K
    11. 1259
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.78
    ViewFeatures
    -0.71
     contextLoads
    -0.62
    󠁴
    -0.62
    getContentPane
    -0.58
    Bioaccumulative
    -0.58
     MainAxisSize
    -0.56
     jegy
    -0.50
    mybatisplus
    -0.49
    ãng
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.71
    BufferException
    0.70
    ThroughAttribute
    0.61
     complexes
    0.59
    oneofs
    0.56
    (!__
    0.54
    bewerken
    0.52
    лючение
    0.50
    clientX
    0.49
     Complexes
    0.48
    Activations Density 1.087%

    No Known Activations