© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11522
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, particularly those involving operators and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Values raised to the power of 2

    np_acts-logits-general · gemini-2.0-flash

    squared terms or powers of 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.76
    fromnode
    -0.72
    <unused8>
    -0.71
    <unused14>
    -0.71
    <unused41>
    -0.71
    [@BOS@]
    -0.71
    <unused16>
    -0.71
    <unused23>
    -0.71
    <unused3>
    -0.70
    <unused17>
    -0.70
    POSITIVE LOGITS
    Squared
    0.51
    sqr
    0.51
     squared
    0.50
     square
    0.47
     Squared
    0.44
    squared
    0.43
     squares
    0.43
     quadratic
    0.42
    square
    0.42
    SQUARE
    0.41
    Activations Density 1.498%

    No Known Activations