© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3742
    Prev
    Next
    INDEX
    Explanations

    references to electron beams and their characteristics in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnitTesting
    -0.49
    MigrationBuilder
    -0.42
    TypedDataSet
    -0.42
     autorytatywna
    -0.41
    endregion
    -0.40
     landscape
    -0.39
     contextLoads
    -0.38
    Appropriate
    -0.38
     Mild
    -0.38
     humane
    -0.37
    POSITIVE LOGITS
    ule
    0.66
     candle
    0.63
     tom
    0.60
     candles
    0.60
    ArrowToggle
    0.57
     bull
    0.57
     Candle
    0.56
    子
    0.56
     Tom
    0.56
    ULE
    0.55
    Activations Density 0.500%

    No Known Activations