© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 3814
    Prev
    Next
    INDEX
    Explanations

    class definitions in a programming context, particularly those extending or implementing other classes or interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‘
    -0.45
    es
    -0.45
     wine
    -0.43
    wir
    -0.43
     dar
    -0.43
    u
    -0.43
    cut
    -0.42
    ar
    -0.42
     “
    -0.42
    ver
    -0.42
    POSITIVE LOGITS
    principalTable
    1.01
     &___
    0.98
    OrBuilder
    0.97
    tagHelperRunner
    0.94
     AssemblyCulture
    0.94
     AssemblyTitle
    0.92
    parsedMessage
    0.91
    tonode
    0.91
    InstrumentedTest
    0.89
    تقاوى
    0.87
    Activations Density 0.120%

    No Known Activations