© 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. 4-GEMMASCOPE-RES-16K
    11. 11517
    Prev
    Next
    INDEX
    Explanations

    occurrences of curly braces and function definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MERCHANTABILITY
    -0.60
     perd
    -0.52
     $\{$
    -0.50
    okra
    -0.50
    λλην
    -0.49
     interpr
    -0.49
     noong
    -0.48
     ciao
    -0.48
    ("$.
    -0.47
     elef
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.76
     ExecuteAsync
    0.74
    endphp
    0.69
    invokeLater
    0.69
    ">—
    0.65
    RegistryLite
    0.64
    IntoConstraints
    0.63
    SqlClient
    0.62
    存于互联网档案馆
    0.62
    SuspendLayout
    0.61
    Activations Density 0.072%

    No Known Activations