© 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. 19-GEMMASCOPE-RES-16K
    11. 3477
    Prev
    Next
    INDEX
    Explanations

    specific syntax elements and structures in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bri
    -0.51
    be
    -0.47
    ym
    -0.47
     ve
    -0.45
    sa
    -0.43
    ذ
    -0.43
    iod
    -0.43
    ü
    -0.42
    選
    -0.42
     whome
    -0.41
    POSITIVE LOGITS
     незавершена
    0.96
    ThroughAttribute
    0.82
     AssemblyCulture
    0.80
    tvguidetime
    0.79
     itſelf
    0.75
     myſelf
    0.74
    ^(@)
    0.73
    verwijspagina
    0.73
    endphp
    0.72
    uxxxx
    0.72
    Activations Density 0.995%

    No Known Activations