© 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. 16-GEMMASCOPE-RES-16K
    11. 7157
    Prev
    Next
    INDEX
    Explanations

    scientific terms and references, particularly in the field of physics and mathematics

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

    Appears before numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and letters in citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.49
     Polly
    -0.48
     Peque
    -0.47
    pulumi
    -0.44
    stock
    -0.44
     EClass
    -0.42
     pains
    -0.42
     stock
    -0.41
     green
    -0.41
     signed
    -0.40
    POSITIVE LOGITS
     Meksiku
    0.78
     Савезне
    0.78
    Chham
    0.69
    complexContent
    0.63
    +:+
    0.62
    expandindo
    0.61
     ivelany
    0.60
    onAttach
    0.58
    Биография
    0.58
     getF
    0.58
    Activations Density 0.804%

    No Known Activations