© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28971
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical reactions, particularly those involving light and energy release

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

    emitting electromagnetic radiation

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     remplacement
    -0.73
     transfers
    -0.63
     replacement
    -0.63
     replacing
    -0.63
     REPLACE
    -0.59
     Replacement
    -0.59
    Replacement
    -0.58
     pindah
    -0.58
     Replacing
    -0.57
    replace
    -0.57
    POSITIVE LOGITS
    UnusedPrivate
    0.69
    ]--;
    0.68
    Enllaces
    0.59
     SEDS
    0.58
     Sorge
    0.56
     []).
    0.56
     kaarangay
    0.55
    Jereo
    0.54
     CountDown
    0.54
     ***!
    0.54
    Activations Density 0.275%

    No Known Activations