© 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. 5-GEMMASCOPE-RES-16K
    11. 13990
    Prev
    Next
    INDEX
    Explanations

    variable declarations or data structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    …
    -0.47
    žel
    -0.46
    onAttach
    -0.41
     molecular
    -0.40
    <eos>
    -0.38
    卧
    -0.37
     …
    -0.37
    PackageManager
    -0.36
     veal
    -0.36
     […]
    -0.35
    POSITIVE LOGITS
    IntoConstraints
    0.99
     تضيفلها
    0.97
     bezeichneter
    0.95
     nahilalakip
    0.89
     ModelExpression
    0.87
    Datuak
    0.82
     дописавши
    0.79
     doInBackground
    0.76
    ArgumentParser
    0.76
     surla
    0.75
    Activations Density 0.078%

    No Known Activations